Legged robots have always been a focal point of research for scholars domestically and internationally.Compared to other types of robots,quadruped robots exhibit superior balance and stability,enabling them to adapt e...Legged robots have always been a focal point of research for scholars domestically and internationally.Compared to other types of robots,quadruped robots exhibit superior balance and stability,enabling them to adapt effectively to diverse environments and traverse rugged terrains.This makes them well-suited for applications such as search and rescue,exploration,and transportation,with strong environmental adaptability,high flexibility,and broad application prospects.This paper discusses the current state of research on quadruped robots in terms of development status,gait trajectory planning methods,motion control strategies,reinforcement learning applications,and control algorithm integration.It highlights advancements in modeling,optimization,control,and data-driven approaches.The study identifies the adoption of efficient gait planning algorithms,the integration of reinforcement learning-based control technologies,and data-driven methods as key directions for the development of quadruped robots.The aim is to provide theoretical references for researchers in the field of quadruped robotics.展开更多
This paper tackles uncertainties between planning and actual models.It extends the concept of RCI(robust control invariant)tubes,originally a parameterized representation of closed-loop control robustness in tradition...This paper tackles uncertainties between planning and actual models.It extends the concept of RCI(robust control invariant)tubes,originally a parameterized representation of closed-loop control robustness in traditional feedback control,to the domain of motion planning for autonomous vehicles.Thus,closed-loop system uncertainty can be preemptively addressed during vehicle motion planning.This involves selecting collision-free trajectories to minimize the volume of robust invariant tubes.Furthermore,constraints on state and control variables are translated into constraints on the RCI tubes of the closed-loop system,ensuring that motion planning produces a safe and optimal trajectory while maintaining flexibility,rather than solely optimizing for the open-loop nominal model.Additionally,to expedite the solving process,we were inspired by L2gain to parameterize the RCI tubes and developed a parameterized explicit iterative expression for propagating ellipsoidal uncertainty sets within closedloop systems.Furthermore,we applied the pseudospectral orthogonal collocation method to parameterize the optimization problem of transcribing trajectories using high-order Lagrangian polynomials.Finally,under various operating conditions,we incorporate both the kinematic and dynamic models of the vehicle and also conduct simulations and analyses of uncertainties such as heading angle measurement,chassis response,and steering hysteresis.Our proposed robust motion planning framework has been validated to effectively address nearly all bounded uncertainties while anticipating potential tracking errors in control during the planning phase.This ensures fast,closed-loop safety and robustness in vehicle motion planning.展开更多
Model mismatches can cause multi-dimensional uncertainties for the receding horizon control strategies of automated vehicles(AVs).The uncertainties may lead to potentially hazardous behaviors when the AV tracks ideal ...Model mismatches can cause multi-dimensional uncertainties for the receding horizon control strategies of automated vehicles(AVs).The uncertainties may lead to potentially hazardous behaviors when the AV tracks ideal trajectories that are individually optimized by the AV's planning layer.To address this issue,this study proposes a safe motion planning and control(SMPAC)framework for AVs.For the control layer,a dynamic model including multi-dimensional uncertainties is established.A zonotopic tube-based robust model predictive control scheme is proposed to constrain the uncertain system in a bounded minimum robust positive invariant set.A flexible tube with varying cross-sections is constructed to reduce the controller conservatism.For the planning layer,a concept of safety sets,representing the geometric boundaries of the ego vehicle and obstacles under uncertainties,is proposed.The safety sets provide the basis for the subsequent evaluation and ranking of the generated trajectories.An efficient collision avoidance algorithm decides the desired trajectory through the intersection detection of the safety sets between the ego vehicle and obstacles.A numerical simulation and hardware-in-the-loop experiment validate the effectiveness and real-time performance of the SMPAC.The result of two driving scenarios indicates that the SMPAC can guarantee the safety of automated driving under multi-dimensional uncertainties.展开更多
The sampling process is very inefficient for sam-pling-based motion planning algorithms that excess random sam-ples are generated in the planning space.In this paper,we pro-pose an adaptive space expansion(ASE)approac...The sampling process is very inefficient for sam-pling-based motion planning algorithms that excess random sam-ples are generated in the planning space.In this paper,we pro-pose an adaptive space expansion(ASE)approach which belongs to the informed sampling category to improve the sampling effi-ciency for quickly finding a feasible path.The ASE method enlarges the search space gradually and restrains the sampling process in a sequence of small hyper-ellipsoid ring subsets to avoid exploring the unnecessary space.Specifically,for a con-structed small hyper-ellipsoid ring subset,if the algorithm cannot find a feasible path in it,then the subset is expanded.Thus,the ASE method successively does space exploring and space expan-sion until the final path has been found.Besides,we present a particular construction method of the hyper-ellipsoid ring that uniform random samples can be directly generated in it.At last,we present a feasible motion planner BiASE and an asymptoti-cally optimal motion planner BiASE*using the bidirectional exploring method and the ASE strategy.Simulations demon-strate that the computation speed is much faster than that of the state-of-the-art algorithms.The source codes are available at https://github.com/shshlei/ompl.展开更多
Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.In this paper,a safe motion planning approach is proposed bas...Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.In this paper,a safe motion planning approach is proposed based on the deep learning-based trajectory prediction method.To begin with,a trajectory prediction model is established based on the graph neural network(GNN)that is trained utilizing the INTERACTION dataset.Then,the validated trajectory prediction model is used to predict the future trajectories of surrounding road users,including pedestrians and vehicles.In addition,a GNN prediction model-enabled motion planner is developed based on the model predictive control technique.Furthermore,two driving scenarios are extracted from the INTERACTION dataset to validate and evaluate the effectiveness of the proposed motion planning approach,i.e.,merging and roundabout scenarios.The results demonstrate that the proposed method can lower the risk and improve driving safety compared with the baseline method.展开更多
Anti-rollover is a critical factor to consider when planning the motion of autonomous heavy trucks.This paper proposed a method for autonomous heavy trucks to generate a path that avoids collisions and minimizes rollo...Anti-rollover is a critical factor to consider when planning the motion of autonomous heavy trucks.This paper proposed a method for autonomous heavy trucks to generate a path that avoids collisions and minimizes rollover risk.The corresponding rollover index is deduced from a 5-DOF heavy truck dynamic model that includes longitudinal motion,lateral motion,yaw motion,sprung mass roll motion,unsprung mass roll motion,and an anti-rollover artificial potential field(APF)is proposed based on this.The motion planning method,which is based on model predictive control(MPC),combines trajectory tracking,anti-rollover APF,and the improved obstacle avoidance APF and considers the truck dynamics constraints,obstacle avoidance,and anti-rollover.Furthermore,by using game theory,the coefficients of the two APF functions are optimised,and an optimal path is planned.The effectiveness of the optimised motion planning method is demonstrated in a variety of scenarios.The results demonstrate that the optimised motion planning method can effectively and efficiently avoid collisions and prevent rollover.展开更多
Non-learning based motion and path planning of an Unmanned Aerial Vehicle(UAV)is faced with low computation efficiency,mapping memory occupation and local optimization problems.This article investigates the challenge ...Non-learning based motion and path planning of an Unmanned Aerial Vehicle(UAV)is faced with low computation efficiency,mapping memory occupation and local optimization problems.This article investigates the challenge of quadrotor control using offline reinforcement learning.By establishing a data-driven learning paradigm that operates without real-environment interaction,the proposed workflow offers a safer approach than traditional reinforcement learning,making it particularly suited for UAV control in industrial scenarios.The introduced algorithm evaluates dataset uncertainty and employs a pessimistic estimation to foster offline deep reinforcement learning.Experiments highlight the algorithm's superiority over traditional online reinforcement learning methods,especially when learning from offline datasets.Furthermore,the article emphasizes the importance of a more general behavior policy.In evaluations,the trained policy demonstrated versatility by adeptly navigating diverse obstacles,underscoring its real-world applicability.展开更多
The motion planning problem for multi-agent systems becomes particularly challenging when humans or human-controlled robots are present in a mixed environment.To address this challenge,this paper presents an interacti...The motion planning problem for multi-agent systems becomes particularly challenging when humans or human-controlled robots are present in a mixed environment.To address this challenge,this paper presents an interaction-aware motion planning approach based on game theory in a receding-horizon manner Leveraging the framework provided by dynamic potential games for handling the interactions among agents,this approach formulates the multi-agent motion planning problem as a differential potential game,highlighting the effectiveness of constrained potential games in facilitating interactive motion planning among agents.Furthermore,online learning techniques are incorporated to dynamically learn the unknown preferences and models of humans or human-controlled robots through the analysis of observed data.To evaluate the effectiveness of the proposed approach,numerical simulations are conducted,demonstrating its capability to generate interactive trajectories for all agents,including humans and human-controlled agents,operating within the mixed environment.The simulation results illustrate the effectiveness of the proposed approach in handling the complexities of multi-agent motion planning in real-world scenarios.展开更多
Image acquisition stands as a prerequisite for scrutinizing surfaces inspection in industrial high-end manufacturing.Current imaging systems often exhibit inflexibility,being confined to specific objects and encounter...Image acquisition stands as a prerequisite for scrutinizing surfaces inspection in industrial high-end manufacturing.Current imaging systems often exhibit inflexibility,being confined to specific objects and encountering difficulties with diverse industrial structures lacking standardized computer-aided design(CAD)models or in instances of deformation.Inspired by the multidimensional observation of humans,our study introduces a universal image acquisition paradigm tailored for robotics,seamlessly integrating multi-objective optimization trajectory planning and control scheme to harness measured point clouds for versatile,efficient,and highly accurate image acquisition across diverse structures and scenarios.Specifically,we introduce an energybased adaptive trajectory optimization(EBATO)method that combines deformation and deviation with dual-threshold optimization and adaptive weight adjustment to improve the smoothness and accuracy of imaging trajectory and posture.Additionally,a multi-optimization control scheme based on a meta-heuristic beetle antennal olfactory recurrent neural network(BAORNN)is proposed to track the imaging trajectory while addressing posture,obstacle avoidance,and physical constraints in industrial scenarios.Simulations,real-world experiments,and comparisons demonstrate the effectiveness and practicality of the proposed paradigm.展开更多
Robotic manipulators increasingly operate in complex three-dimensional workspaces where accuracy and strict limits on position,velocity,and acceleration must be satisfied.Conventional geometric planners emphasize path...Robotic manipulators increasingly operate in complex three-dimensional workspaces where accuracy and strict limits on position,velocity,and acceleration must be satisfied.Conventional geometric planners emphasize path smoothness but often ignore dynamic feasibility,motivating control-aware trajectory generation.This study presents a novel model predictive control(MPC)framework for three-dimensional trajectory planning of robotic manipulators that integrates second-order dynamic modeling and multi-objective parameter optimization.Unlike conventional interpolation techniques such as cubic splines,B-splines,and linear interpolation,which neglect physical constraints and system dynamics,the proposed method generates dynamically feasible trajectories by directly optimizing over acceleration inputs while minimizing both tracking error and control effort.A key innovation lies in the use of Pareto front analysis for tuning prediction horizon and sampling time,enabling a systematic balance between accuracy and motion smoothness.Comparative evaluation using simulated experiments demonstrates that the proposed MPC approach achieves a minimum mean absolute error(MAE)of 0.170 and reduces maximum acceleration to 0.0217,compared to 0.0385 in classical linear methods.The maximum deviation error was also reduced by approximately 27.4%relative to MPC configurations without tuned parameters.All experiments were conducted in a simulation environment,with computational times per control cycle consistently remaining below 20 milliseconds,indicating practical feasibility for real-time applications.Thiswork advances the state-of-the-art inMPC-based trajectory planning by offering a scalable and interpretable control architecture that meets physical constraints while optimizing motion efficiency,thus making it suitable for deployment in safety-critical robotic applications.展开更多
Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framew...Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human drivers.Moreover, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.展开更多
This paper is concerned with optimal motion planning for vibration reducing of free-floating flexible redundant manipulators. Firstly, dynamic model of the system is established based on Lagrange method, and the motio...This paper is concerned with optimal motion planning for vibration reducing of free-floating flexible redundant manipulators. Firstly, dynamic model of the system is established based on Lagrange method, and the motion planning model for vibration reducing is proposed. Secondly, a hybrid optimization approach employing Gauss pseudospectral method （GPM） and direct shooting method （DSM）, is proposed to solve the motion planning problem. In this approach, the motion planning problem is transformed into a non-linear parameter optimization problem using GPM, and genetic algorithm （GA） is employed to locate the approximate solution. Subsequently, an optimization model is formulated based on DSM, and sequential quadratic programming （SQP） algorithm is used to obtain the accurate solution, with the approximate solution as an initial reference solution. Finally, several numerical simulations are investigated, and the global vibration or residual vibration of flexible link is obviously reduced by the joint trajectory which is obtained by the hybrid optimization approach. The numerical simulation results indicate that the approach is effective and stable to the motion planning problem of vibration reducing.展开更多
The current motion planning approaches for redundant manipulators mainly includes two categories： improved gradient-projection method and some other efficiency numerical methods. The former is excessively sensitive t...The current motion planning approaches for redundant manipulators mainly includes two categories： improved gradient-projection method and some other efficiency numerical methods. The former is excessively sensitive to parameters, which makes adjustment difficult; and the latter treats the motion planning as general task by ignoring the particularity, which has good universal property but reduces the solving speed for on-line real-time planning. In this paper, a novel stepwise solution based on self-motion manifold is proposed for motion planning of redundant manipulators, namely, the chief tasks and secondary tasks are implemented step by step. Firstly, the posture tracking of end-effector is achieved accurately by employing the non-redundant joint. Secondly, the end-effector is set to keep stationary. Finally, self-motion of manipulator is realized via additional work on the gradient of redundant joint displacement. To verify this solution, experiments of round obstacle avoiding are carried out via the planar 3 degree-of-~eedom manipulator. And the experimental results indicate that this motion planning algorithm can effectively achieve obstacle avoiding and posture tracking of the end-effector. Compared with traditional gradient projection method, this approach can accelerate the problem-solving process, and is more applicable to obstacle avoiding and other additional work in displacement level.展开更多
Hydraulic excavator is one type of the most widely applied construction equipment for various applications mainly because of its versatility and mobility. Among the tasks performed by a hydraulic excavator, repeatable...Hydraulic excavator is one type of the most widely applied construction equipment for various applications mainly because of its versatility and mobility. Among the tasks performed by a hydraulic excavator, repeatable level digging or flat surface finishing may take a large percentage. Using automated functions to perform such repeatable and tedious jobs will not only greatly increase the overall productivity but more importantly also improve the operation safety. For the purpose of investigating the technology without loss of generality, this research is conducted to create a coordinate control method for the boom, arm and bucket cylinders on a hydraulic excavator to perform accurate and effective works. On the basis of the kinematic analysis of the excavator linkage system, the tip trajectory of the end-effector can be determined in terms of three hydraulic cylinders coordinated motion with a visualized method. The coordination of those hydraulic cylinders is realized by controlling three electro-hydraulic proportional valves coordinately. Therefore, the complex control algorithm of a hydraulic excavator can be simplified into coordinated motion control of three individual systems. This coordinate control algorithm was validated on a wheeled hydraulic excavator, and the validation results indicated that this developed control method could satisfactorily accomplish the auto-digging function for level digging or flat surface finishing.展开更多
Motion planning is critical to realize the autonomous operation of mobile robots.As the complexity and randomness of robot application scenarios increase,the planning capability of the classical hierarchical motion pl...Motion planning is critical to realize the autonomous operation of mobile robots.As the complexity and randomness of robot application scenarios increase,the planning capability of the classical hierarchical motion planners is challenged.With the development of machine learning,the deep reinforcement learning(DRL)-based motion planner has gradually become a research hotspot due to its several advantageous feature.The DRL-based motion planner is model-free and does not rely on the prior structured map.Most importantly,the DRL-based motion planner achieves the unification of the global planner and the local planner.In this paper,we provide a systematic review of various motion planning methods.Firstly,we summarize the representative and state-of-the-art works for each submodule of the classical motion planning architecture and analyze their performance features.Then,we concentrate on summarizing reinforcement learning(RL)-based motion planning approaches,including motion planners combined with RL improvements,map-free RL-based motion planners,and multi-robot cooperative planning methods.Finally,we analyze the urgent challenges faced by these mainstream RLbased motion planners in detail,review some state-of-the-art works for these issues,and propose suggestions for future research.展开更多
There is an increasing awareness of the need to reduce traffic accidents and fatality due to vehicle collision.Post-impact hazards can be more serious as the driver may fail to maintain effective control after collisi...There is an increasing awareness of the need to reduce traffic accidents and fatality due to vehicle collision.Post-impact hazards can be more serious as the driver may fail to maintain effective control after collisions.To avoid subsequent crash events and to stabilize the vehicle,this paper proposes a post-impact motion planning and stability control method for autonomous vehicles.An enabling motion planning method is proposed for post-impact situations by combining the polynomial curve and artificial potential field while considering obstacle avoidance.A hierarchical controller that consists of an upper and a lower controller is then developed to track the planned motion.In the upper controller,a time-varying linear quadratic regulator is presented to calculate the desired generalized forces.In the lower controller,a nonlinear-optimization-based torque allocation algorithm is proposed to optimally coordinate the actuators to realize the desired generalized forces.The proposed scheme is verified under comprehensive driving scenarios through hardware-in-loop tests.展开更多
Unmanned Aerial Vehicles(UAVs)play a vital role in military warfare.In a variety of battlefield mission scenarios,UAVs are required to safely fly to designated locations without human intervention.Therefore,finding a ...Unmanned Aerial Vehicles(UAVs)play a vital role in military warfare.In a variety of battlefield mission scenarios,UAVs are required to safely fly to designated locations without human intervention.Therefore,finding a suitable method to solve the UAV Autonomous Motion Planning(AMP)problem can improve the success rate of UAV missions to a certain extent.In recent years,many studies have used Deep Reinforcement Learning(DRL)methods to address the AMP problem and have achieved good results.From the perspective of sampling,this paper designs a sampling method with double-screening,combines it with the Deep Deterministic Policy Gradient(DDPG)algorithm,and proposes the Relevant Experience Learning-DDPG(REL-DDPG)algorithm.The REL-DDPG algorithm uses a Prioritized Experience Replay(PER)mechanism to break the correlation of continuous experiences in the experience pool,finds the experiences most similar to the current state to learn according to the theory in human education,and expands the influence of the learning process on action selection at the current state.All experiments are applied in a complex unknown simulation environment constructed based on the parameters of a real UAV.The training experiments show that REL-DDPG improves the convergence speed and the convergence result compared to the state-of-the-art DDPG algorithm,while the testing experiments show the applicability of the algorithm and investigate the performance under different parameter conditions.展开更多
Autonomous marine vehicles(AMVs)have received considerable attention in the past few decades,mainly because they play essential roles in broad marine applications such as environmental monitoring and resource explorat...Autonomous marine vehicles(AMVs)have received considerable attention in the past few decades,mainly because they play essential roles in broad marine applications such as environmental monitoring and resource exploration.Recent advances in the field of communication technologies,perception capability,computational power and advanced optimization algorithms have stimulated new interest in the development of AMVs.In order to deploy the constrained AMVs in the complex dynamic maritime environment,it is crucial to enhance the guidance and control capabilities through effective and practical planning,and control algorithms.Model predictive control(MPC)has been exceptionally successful in different fields due to its ability to systematically handle constraints while optimizing control performance.This paper aims to provide a review of recent progress in the context of motion planning and control for AMVs from the perceptive of MPC.Finally,future research trends and directions in this substantial research area of AMVs are highlighted.展开更多
It is very necessary for an intelligent heavy truck to have the ability to prevent rollover independently.However,it was rarely considered in intelligent vehicle motion planning.To improve rollover stability,a motion ...It is very necessary for an intelligent heavy truck to have the ability to prevent rollover independently.However,it was rarely considered in intelligent vehicle motion planning.To improve rollover stability,a motion planning strategy with autonomous anti rollover ability for an intelligent heavy truck is put forward in this paper.Considering the influence of unsprung mass in the front axle and the rear axle and the body roll stiffness on vehicle rollover stability,a rollover dynamics model is built for the intelligent heavy truck.From the model,a novel rollover index is derived to evaluate vehicle rollover risk accurately,and a model predictive control algorithm is applicated to design the motion planning strategy for the intelligent heavy truck,which integrates the vehicle rollover stability,the artificial potential field for the obstacle avoidance,the path tracking and vehicle dynamics constrains.Then,the optimal path is obtained to meet the requirements that the intelligent heavy truck can avoid obstacles and drive stably without rollover.In addition,three typical scenarios are designed to numerically simulate the dynamic performance of the intelligent heavy truck.The results show that the proposed motion planning strategy can avoid collisions and improve vehicle rollover stability effectively even under the worst driving scenarios.展开更多
基金funded by the Natural Science Basis Research Plan in Shaanxi Province of China(Program No.2023-JC-QN-0659)General Specialized Scientific Research Program of the Shaanxi Provincial Department of Education(Program 23JK0349).
文摘Legged robots have always been a focal point of research for scholars domestically and internationally.Compared to other types of robots,quadruped robots exhibit superior balance and stability,enabling them to adapt effectively to diverse environments and traverse rugged terrains.This makes them well-suited for applications such as search and rescue,exploration,and transportation,with strong environmental adaptability,high flexibility,and broad application prospects.This paper discusses the current state of research on quadruped robots in terms of development status,gait trajectory planning methods,motion control strategies,reinforcement learning applications,and control algorithm integration.It highlights advancements in modeling,optimization,control,and data-driven approaches.The study identifies the adoption of efficient gait planning algorithms,the integration of reinforcement learning-based control technologies,and data-driven methods as key directions for the development of quadruped robots.The aim is to provide theoretical references for researchers in the field of quadruped robotics.
基金Supported by National Natural Science Foundation of China(Grant Nos.52025121,52394263)National Key R&D Plan of China(Grant No.2023YFD2000301)+2 种基金Foundation of State Key Laboratory of Automobile Safety and Energy Saving of China(Grant No.KFZ2201)the Jiangsu Provincial Scientific Research Center of Applied Mathematics under(Grant No.BK20233002)Special Fund of Jiangsu Province for the Transformation of Scientific and Technological Achievements under(Grant No.BA2021023)。
文摘This paper tackles uncertainties between planning and actual models.It extends the concept of RCI(robust control invariant)tubes,originally a parameterized representation of closed-loop control robustness in traditional feedback control,to the domain of motion planning for autonomous vehicles.Thus,closed-loop system uncertainty can be preemptively addressed during vehicle motion planning.This involves selecting collision-free trajectories to minimize the volume of robust invariant tubes.Furthermore,constraints on state and control variables are translated into constraints on the RCI tubes of the closed-loop system,ensuring that motion planning produces a safe and optimal trajectory while maintaining flexibility,rather than solely optimizing for the open-loop nominal model.Additionally,to expedite the solving process,we were inspired by L2gain to parameterize the RCI tubes and developed a parameterized explicit iterative expression for propagating ellipsoidal uncertainty sets within closedloop systems.Furthermore,we applied the pseudospectral orthogonal collocation method to parameterize the optimization problem of transcribing trajectories using high-order Lagrangian polynomials.Finally,under various operating conditions,we incorporate both the kinematic and dynamic models of the vehicle and also conduct simulations and analyses of uncertainties such as heading angle measurement,chassis response,and steering hysteresis.Our proposed robust motion planning framework has been validated to effectively address nearly all bounded uncertainties while anticipating potential tracking errors in control during the planning phase.This ensures fast,closed-loop safety and robustness in vehicle motion planning.
基金supported by the National Natural Science Foundation of China(51875061)China Scholarship Council(202206050107)。
文摘Model mismatches can cause multi-dimensional uncertainties for the receding horizon control strategies of automated vehicles(AVs).The uncertainties may lead to potentially hazardous behaviors when the AV tracks ideal trajectories that are individually optimized by the AV's planning layer.To address this issue,this study proposes a safe motion planning and control(SMPAC)framework for AVs.For the control layer,a dynamic model including multi-dimensional uncertainties is established.A zonotopic tube-based robust model predictive control scheme is proposed to constrain the uncertain system in a bounded minimum robust positive invariant set.A flexible tube with varying cross-sections is constructed to reduce the controller conservatism.For the planning layer,a concept of safety sets,representing the geometric boundaries of the ego vehicle and obstacles under uncertainties,is proposed.The safety sets provide the basis for the subsequent evaluation and ranking of the generated trajectories.An efficient collision avoidance algorithm decides the desired trajectory through the intersection detection of the safety sets between the ego vehicle and obstacles.A numerical simulation and hardware-in-the-loop experiment validate the effectiveness and real-time performance of the SMPAC.The result of two driving scenarios indicates that the SMPAC can guarantee the safety of automated driving under multi-dimensional uncertainties.
基金supported in part by the National Natural Science Foun-dation of China(51975236)the National Key Research and Development Program of China(2018YFA0703203)the Innovation Project of Optics Valley Laboratory(OVL2021BG007)。
文摘The sampling process is very inefficient for sam-pling-based motion planning algorithms that excess random sam-ples are generated in the planning space.In this paper,we pro-pose an adaptive space expansion(ASE)approach which belongs to the informed sampling category to improve the sampling effi-ciency for quickly finding a feasible path.The ASE method enlarges the search space gradually and restrains the sampling process in a sequence of small hyper-ellipsoid ring subsets to avoid exploring the unnecessary space.Specifically,for a con-structed small hyper-ellipsoid ring subset,if the algorithm cannot find a feasible path in it,then the subset is expanded.Thus,the ASE method successively does space exploring and space expan-sion until the final path has been found.Besides,we present a particular construction method of the hyper-ellipsoid ring that uniform random samples can be directly generated in it.At last,we present a feasible motion planner BiASE and an asymptoti-cally optimal motion planner BiASE*using the bidirectional exploring method and the ASE strategy.Simulations demon-strate that the computation speed is much faster than that of the state-of-the-art algorithms.The source codes are available at https://github.com/shshlei/ompl.
基金Supported by National Natural Science Foundation of China(Grant Nos.52222215,52072051)Chongqing Municipal Natural Science Foundation of China(Grant No.CSTB2023NSCQ-JQX0003).
文摘Accurate trajectory prediction of surrounding road users is the fundamental input for motion planning,which enables safe autonomous driving on public roads.In this paper,a safe motion planning approach is proposed based on the deep learning-based trajectory prediction method.To begin with,a trajectory prediction model is established based on the graph neural network(GNN)that is trained utilizing the INTERACTION dataset.Then,the validated trajectory prediction model is used to predict the future trajectories of surrounding road users,including pedestrians and vehicles.In addition,a GNN prediction model-enabled motion planner is developed based on the model predictive control technique.Furthermore,two driving scenarios are extracted from the INTERACTION dataset to validate and evaluate the effectiveness of the proposed motion planning approach,i.e.,merging and roundabout scenarios.The results demonstrate that the proposed method can lower the risk and improve driving safety compared with the baseline method.
基金Supported by National Natural Science Foundation of China(Grant No.51775269)Jiangsu Provincial Natural Science Foundation of China(Grant No.BK20211190).
文摘Anti-rollover is a critical factor to consider when planning the motion of autonomous heavy trucks.This paper proposed a method for autonomous heavy trucks to generate a path that avoids collisions and minimizes rollover risk.The corresponding rollover index is deduced from a 5-DOF heavy truck dynamic model that includes longitudinal motion,lateral motion,yaw motion,sprung mass roll motion,unsprung mass roll motion,and an anti-rollover artificial potential field(APF)is proposed based on this.The motion planning method,which is based on model predictive control(MPC),combines trajectory tracking,anti-rollover APF,and the improved obstacle avoidance APF and considers the truck dynamics constraints,obstacle avoidance,and anti-rollover.Furthermore,by using game theory,the coefficients of the two APF functions are optimised,and an optimal path is planned.The effectiveness of the optimised motion planning method is demonstrated in a variety of scenarios.The results demonstrate that the optimised motion planning method can effectively and efficiently avoid collisions and prevent rollover.
基金supported by the National Natural Science Foundation of China(No.52272382)the Aeronautical Science Foundation of China(No.20200017051001)the Fundamental Research Funds for the Central Universities,China。
文摘Non-learning based motion and path planning of an Unmanned Aerial Vehicle(UAV)is faced with low computation efficiency,mapping memory occupation and local optimization problems.This article investigates the challenge of quadrotor control using offline reinforcement learning.By establishing a data-driven learning paradigm that operates without real-environment interaction,the proposed workflow offers a safer approach than traditional reinforcement learning,making it particularly suited for UAV control in industrial scenarios.The introduced algorithm evaluates dataset uncertainty and employs a pessimistic estimation to foster offline deep reinforcement learning.Experiments highlight the algorithm's superiority over traditional online reinforcement learning methods,especially when learning from offline datasets.Furthermore,the article emphasizes the importance of a more general behavior policy.In evaluations,the trained policy demonstrated versatility by adeptly navigating diverse obstacles,underscoring its real-world applicability.
基金supported by the A*STAR under its"RIE2025 IAF-PP Advanced ROS2-native Platform Technologies for Cross sectorial Robotics Adoption(M21K1a0104)"programme.
文摘The motion planning problem for multi-agent systems becomes particularly challenging when humans or human-controlled robots are present in a mixed environment.To address this challenge,this paper presents an interaction-aware motion planning approach based on game theory in a receding-horizon manner Leveraging the framework provided by dynamic potential games for handling the interactions among agents,this approach formulates the multi-agent motion planning problem as a differential potential game,highlighting the effectiveness of constrained potential games in facilitating interactive motion planning among agents.Furthermore,online learning techniques are incorporated to dynamically learn the unknown preferences and models of humans or human-controlled robots through the analysis of observed data.To evaluate the effectiveness of the proposed approach,numerical simulations are conducted,demonstrating its capability to generate interactive trajectories for all agents,including humans and human-controlled agents,operating within the mixed environment.The simulation results illustrate the effectiveness of the proposed approach in handling the complexities of multi-agent motion planning in real-world scenarios.
基金supported in part by the National Natural Science Foundation of China(62303457,U21A20482)China Postdoctoral Science Foundation(2023M733737)the National Key Research and Development Program of China(2022YFB3303800)。
文摘Image acquisition stands as a prerequisite for scrutinizing surfaces inspection in industrial high-end manufacturing.Current imaging systems often exhibit inflexibility,being confined to specific objects and encountering difficulties with diverse industrial structures lacking standardized computer-aided design(CAD)models or in instances of deformation.Inspired by the multidimensional observation of humans,our study introduces a universal image acquisition paradigm tailored for robotics,seamlessly integrating multi-objective optimization trajectory planning and control scheme to harness measured point clouds for versatile,efficient,and highly accurate image acquisition across diverse structures and scenarios.Specifically,we introduce an energybased adaptive trajectory optimization(EBATO)method that combines deformation and deviation with dual-threshold optimization and adaptive weight adjustment to improve the smoothness and accuracy of imaging trajectory and posture.Additionally,a multi-optimization control scheme based on a meta-heuristic beetle antennal olfactory recurrent neural network(BAORNN)is proposed to track the imaging trajectory while addressing posture,obstacle avoidance,and physical constraints in industrial scenarios.Simulations,real-world experiments,and comparisons demonstrate the effectiveness and practicality of the proposed paradigm.
基金funded by the research project“BR24992947—Development of Robots,Scientific,Technical,and Software for Flexible Robotization and Industrial Automation(RPA)in Automotive Industrial Enterprises in Kazakhstan Using Artificial Intelligence”.
文摘Robotic manipulators increasingly operate in complex three-dimensional workspaces where accuracy and strict limits on position,velocity,and acceleration must be satisfied.Conventional geometric planners emphasize path smoothness but often ignore dynamic feasibility,motivating control-aware trajectory generation.This study presents a novel model predictive control(MPC)framework for three-dimensional trajectory planning of robotic manipulators that integrates second-order dynamic modeling and multi-objective parameter optimization.Unlike conventional interpolation techniques such as cubic splines,B-splines,and linear interpolation,which neglect physical constraints and system dynamics,the proposed method generates dynamically feasible trajectories by directly optimizing over acceleration inputs while minimizing both tracking error and control effort.A key innovation lies in the use of Pareto front analysis for tuning prediction horizon and sampling time,enabling a systematic balance between accuracy and motion smoothness.Comparative evaluation using simulated experiments demonstrates that the proposed MPC approach achieves a minimum mean absolute error(MAE)of 0.170 and reduces maximum acceleration to 0.0217,compared to 0.0385 in classical linear methods.The maximum deviation error was also reduced by approximately 27.4%relative to MPC configurations without tuned parameters.All experiments were conducted in a simulation environment,with computational times per control cycle consistently remaining below 20 milliseconds,indicating practical feasibility for real-time applications.Thiswork advances the state-of-the-art inMPC-based trajectory planning by offering a scalable and interpretable control architecture that meets physical constraints while optimizing motion efficiency,thus making it suitable for deployment in safety-critical robotic applications.
基金supported in part by the National Natural Science Foundation of China (61773414,61806076)Hubei Provincial Natural Science Foundation of China (2018CFB158)
文摘Motion planning is one of the most significant technologies for autonomous driving. To make motion planning models able to learn from the environment and to deal with emergency situations, a new motion planning framework called as"parallel planning" is proposed in this paper. In order to generate sufficient and various training samples, artificial traffic scenes are firstly constructed based on the knowledge from the reality.A deep planning model which combines a convolutional neural network(CNN) with the Long Short-Term Memory module(LSTM) is developed to make planning decisions in an end-toend mode. This model can learn from both real and artificial traffic scenes and imitate the driving style of human drivers.Moreover, a parallel deep reinforcement learning approach is also presented to improve the robustness of planning model and reduce the error rate. To handle emergency situations, a hybrid generative model including a variational auto-encoder(VAE) and a generative adversarial network(GAN) is utilized to learn from virtual emergencies generated in artificial traffic scenes. While an autonomous vehicle is moving, the hybrid generative model generates multiple video clips in parallel, which correspond to different potential emergency scenarios. Simultaneously, the deep planning model makes planning decisions for both virtual and current real scenes. The final planning decision is determined by analysis of real observations. Leveraging the parallel planning approach, the planner is able to make rational decisions without heavy calculation burden when an emergency occurs.
基金National Natural Science Foundation of China （10902121）
文摘This paper is concerned with optimal motion planning for vibration reducing of free-floating flexible redundant manipulators. Firstly, dynamic model of the system is established based on Lagrange method, and the motion planning model for vibration reducing is proposed. Secondly, a hybrid optimization approach employing Gauss pseudospectral method （GPM） and direct shooting method （DSM）, is proposed to solve the motion planning problem. In this approach, the motion planning problem is transformed into a non-linear parameter optimization problem using GPM, and genetic algorithm （GA） is employed to locate the approximate solution. Subsequently, an optimization model is formulated based on DSM, and sequential quadratic programming （SQP） algorithm is used to obtain the accurate solution, with the approximate solution as an initial reference solution. Finally, several numerical simulations are investigated, and the global vibration or residual vibration of flexible link is obviously reduced by the joint trajectory which is obtained by the hybrid optimization approach. The numerical simulation results indicate that the approach is effective and stable to the motion planning problem of vibration reducing.
基金supported by National Hi-tech Research and Develop- ment Program of China (863 Program, Grant No. 2005AA404291)
文摘The current motion planning approaches for redundant manipulators mainly includes two categories： improved gradient-projection method and some other efficiency numerical methods. The former is excessively sensitive to parameters, which makes adjustment difficult; and the latter treats the motion planning as general task by ignoring the particularity, which has good universal property but reduces the solving speed for on-line real-time planning. In this paper, a novel stepwise solution based on self-motion manifold is proposed for motion planning of redundant manipulators, namely, the chief tasks and secondary tasks are implemented step by step. Firstly, the posture tracking of end-effector is achieved accurately by employing the non-redundant joint. Secondly, the end-effector is set to keep stationary. Finally, self-motion of manipulator is realized via additional work on the gradient of redundant joint displacement. To verify this solution, experiments of round obstacle avoiding are carried out via the planar 3 degree-of-~eedom manipulator. And the experimental results indicate that this motion planning algorithm can effectively achieve obstacle avoiding and posture tracking of the end-effector. Compared with traditional gradient projection method, this approach can accelerate the problem-solving process, and is more applicable to obstacle avoiding and other additional work in displacement level.
基金supported by National Natural Science Foundation of China (Grant No. 50875228)
文摘Hydraulic excavator is one type of the most widely applied construction equipment for various applications mainly because of its versatility and mobility. Among the tasks performed by a hydraulic excavator, repeatable level digging or flat surface finishing may take a large percentage. Using automated functions to perform such repeatable and tedious jobs will not only greatly increase the overall productivity but more importantly also improve the operation safety. For the purpose of investigating the technology without loss of generality, this research is conducted to create a coordinate control method for the boom, arm and bucket cylinders on a hydraulic excavator to perform accurate and effective works. On the basis of the kinematic analysis of the excavator linkage system, the tip trajectory of the end-effector can be determined in terms of three hydraulic cylinders coordinated motion with a visualized method. The coordination of those hydraulic cylinders is realized by controlling three electro-hydraulic proportional valves coordinately. Therefore, the complex control algorithm of a hydraulic excavator can be simplified into coordinated motion control of three individual systems. This coordinate control algorithm was validated on a wheeled hydraulic excavator, and the validation results indicated that this developed control method could satisfactorily accomplish the auto-digging function for level digging or flat surface finishing.
基金supported by the National Natural Science Foundation of China (62173251)the“Zhishan”Scholars Programs of Southeast University+1 种基金the Fundamental Research Funds for the Central UniversitiesShanghai Gaofeng&Gaoyuan Project for University Academic Program Development (22120210022)
文摘Motion planning is critical to realize the autonomous operation of mobile robots.As the complexity and randomness of robot application scenarios increase,the planning capability of the classical hierarchical motion planners is challenged.With the development of machine learning,the deep reinforcement learning(DRL)-based motion planner has gradually become a research hotspot due to its several advantageous feature.The DRL-based motion planner is model-free and does not rely on the prior structured map.Most importantly,the DRL-based motion planner achieves the unification of the global planner and the local planner.In this paper,we provide a systematic review of various motion planning methods.Firstly,we summarize the representative and state-of-the-art works for each submodule of the classical motion planning architecture and analyze their performance features.Then,we concentrate on summarizing reinforcement learning(RL)-based motion planning approaches,including motion planners combined with RL improvements,map-free RL-based motion planners,and multi-robot cooperative planning methods.Finally,we analyze the urgent challenges faced by these mainstream RLbased motion planners in detail,review some state-of-the-art works for these issues,and propose suggestions for future research.
基金Beijing Municipal Science and Technology Commission via the Beijing Nova Program(Grant No.Z201100006820007).
文摘There is an increasing awareness of the need to reduce traffic accidents and fatality due to vehicle collision.Post-impact hazards can be more serious as the driver may fail to maintain effective control after collisions.To avoid subsequent crash events and to stabilize the vehicle,this paper proposes a post-impact motion planning and stability control method for autonomous vehicles.An enabling motion planning method is proposed for post-impact situations by combining the polynomial curve and artificial potential field while considering obstacle avoidance.A hierarchical controller that consists of an upper and a lower controller is then developed to track the planned motion.In the upper controller,a time-varying linear quadratic regulator is presented to calculate the desired generalized forces.In the lower controller,a nonlinear-optimization-based torque allocation algorithm is proposed to optimally coordinate the actuators to realize the desired generalized forces.The proposed scheme is verified under comprehensive driving scenarios through hardware-in-loop tests.
基金co-supported by the National Natural Science Foundation of China(Nos.62003267,61573285)the Aeronautical Science Foundation of China(ASFC)(No.20175553027)Natural Science Basic Research Plan in Shaanxi Province of China(No.2020JQ-220)。
文摘Unmanned Aerial Vehicles(UAVs)play a vital role in military warfare.In a variety of battlefield mission scenarios,UAVs are required to safely fly to designated locations without human intervention.Therefore,finding a suitable method to solve the UAV Autonomous Motion Planning(AMP)problem can improve the success rate of UAV missions to a certain extent.In recent years,many studies have used Deep Reinforcement Learning(DRL)methods to address the AMP problem and have achieved good results.From the perspective of sampling,this paper designs a sampling method with double-screening,combines it with the Deep Deterministic Policy Gradient(DDPG)algorithm,and proposes the Relevant Experience Learning-DDPG(REL-DDPG)algorithm.The REL-DDPG algorithm uses a Prioritized Experience Replay(PER)mechanism to break the correlation of continuous experiences in the experience pool,finds the experiences most similar to the current state to learn according to the theory in human education,and expands the influence of the learning process on action selection at the current state.All experiments are applied in a complex unknown simulation environment constructed based on the parameters of a real UAV.The training experiments show that REL-DDPG improves the convergence speed and the convergence result compared to the state-of-the-art DDPG algorithm,while the testing experiments show the applicability of the algorithm and investigate the performance under different parameter conditions.
基金supported by the Natural Sciences and Engineering Research Council of Canada(NSERC)。
文摘Autonomous marine vehicles(AMVs)have received considerable attention in the past few decades,mainly because they play essential roles in broad marine applications such as environmental monitoring and resource exploration.Recent advances in the field of communication technologies,perception capability,computational power and advanced optimization algorithms have stimulated new interest in the development of AMVs.In order to deploy the constrained AMVs in the complex dynamic maritime environment,it is crucial to enhance the guidance and control capabilities through effective and practical planning,and control algorithms.Model predictive control(MPC)has been exceptionally successful in different fields due to its ability to systematically handle constraints while optimizing control performance.This paper aims to provide a review of recent progress in the context of motion planning and control for AMVs from the perceptive of MPC.Finally,future research trends and directions in this substantial research area of AMVs are highlighted.
基金Supported by National Natural Science Foundation of China(Grant Nos.51775269,U1964203,52072215)National Key R&D Program of China(Grant No.2020YFB1600303).
文摘It is very necessary for an intelligent heavy truck to have the ability to prevent rollover independently.However,it was rarely considered in intelligent vehicle motion planning.To improve rollover stability,a motion planning strategy with autonomous anti rollover ability for an intelligent heavy truck is put forward in this paper.Considering the influence of unsprung mass in the front axle and the rear axle and the body roll stiffness on vehicle rollover stability,a rollover dynamics model is built for the intelligent heavy truck.From the model,a novel rollover index is derived to evaluate vehicle rollover risk accurately,and a model predictive control algorithm is applicated to design the motion planning strategy for the intelligent heavy truck,which integrates the vehicle rollover stability,the artificial potential field for the obstacle avoidance,the path tracking and vehicle dynamics constrains.Then,the optimal path is obtained to meet the requirements that the intelligent heavy truck can avoid obstacles and drive stably without rollover.In addition,three typical scenarios are designed to numerically simulate the dynamic performance of the intelligent heavy truck.The results show that the proposed motion planning strategy can avoid collisions and improve vehicle rollover stability effectively even under the worst driving scenarios.
