The forward design of trajectory planning strategies requires preset trajectory optimization functions,resulting in poor adaptability of the strategy and an inability to accurately generate obstacle avoidance trajecto...The forward design of trajectory planning strategies requires preset trajectory optimization functions,resulting in poor adaptability of the strategy and an inability to accurately generate obstacle avoidance trajectories that conform to real driver behavior habits.In addition,owing to the strong time-varying dynamic characteristics of obstacle avoidance scenarios,it is necessary to design numerous trajectory optimization functions and adjust the corresponding parameters.Therefore,an anthropomorphic obstacle-avoidance trajectory planning strategy for adaptive driving scenarios is proposed.First,numerous expert-demonstrated trajectories are extracted from the HighD natural driving dataset.Subsequently,a trajectory expectation feature-matching algorithm is proposed that uses maximum entropy inverse reinforcement learning theory to learn the extracted expert-demonstrated trajectories and achieve automatic acquisition of the optimization function of the expert-demonstrated trajectory.Furthermore,a mapping model is constructed by combining the key driving scenario information that affects vehicle obstacle avoidance with the weight of the optimization function,and an anthropomorphic obstacle avoidance trajectory planning strategy for adaptive driving scenarios is proposed.Finally,the proposed strategy is verified based on real driving scenarios.The results show that the strategy can adjust the weight distribution of the trajectory optimization function in real time according to the“emergency degree”of obstacle avoidance and the state of the vehicle.Moreover,this strategy can generate anthropomorphic trajectories that are similar to expert-demonstrated trajectories,effectively improving the adaptability and acceptability of trajectories in driving scenarios.展开更多
Abstract Cities based on coal resources have increasingly important social and economic roles in China. Their strategies for sustainable development, however, urgently need to be improved, which represents a huge chal...Abstract Cities based on coal resources have increasingly important social and economic roles in China. Their strategies for sustainable development, however, urgently need to be improved, which represents a huge challenge. Most observers believe that the continued progress of these cities relies on the optimization of scientific adaptive management in which social, economic, and ecological factors are incorporated. A systems perspective that combines policies, management priorities, and long-term policy impacts needs to be applied. To date, however, such an approach has not been adopted, which means it is difficult to implement adaptive management at the regional scale. In this study, we used various situations to develop a multiple adaptive scenario system dynamics model. We then simulated a range of policy scenarios, with Ordos in the Inner Mongolia Autonomous Region as a case study. Simulation results showed that the current strategy is not sustainable and predicted that the system would exceed the environmental capacity, with risks of resource exhaustion and urban decline in 2025-2035. Five critical policy variables, including the urban population carrying capacity, rates of water consumption and water recycling, and expansion of urban land cover, were identified during sensitivity analysis. We developed and compared six socio-economic scenarios. The urban area, represented by the urban population density, seemed to transition through five different stages, namely natural growth, rapid growth, stable oscillation, fading, and rebalancing. Our scenarios suggested that different policies had different roles through each stage. The water use efficiency management policy had a comprehensive far-reaching influence on the system behavior; land urbanization management functions dominated at the start, and population capacity management was a major control in the mid-term. Our results showed that the water recycling policy and the urban population carrying capacity were extremely important, and both should be reinforced and evaluated by the local governments.展开更多
基金supported by the National Natural Science Foundation of China(51875302)。
文摘The forward design of trajectory planning strategies requires preset trajectory optimization functions,resulting in poor adaptability of the strategy and an inability to accurately generate obstacle avoidance trajectories that conform to real driver behavior habits.In addition,owing to the strong time-varying dynamic characteristics of obstacle avoidance scenarios,it is necessary to design numerous trajectory optimization functions and adjust the corresponding parameters.Therefore,an anthropomorphic obstacle-avoidance trajectory planning strategy for adaptive driving scenarios is proposed.First,numerous expert-demonstrated trajectories are extracted from the HighD natural driving dataset.Subsequently,a trajectory expectation feature-matching algorithm is proposed that uses maximum entropy inverse reinforcement learning theory to learn the extracted expert-demonstrated trajectories and achieve automatic acquisition of the optimization function of the expert-demonstrated trajectory.Furthermore,a mapping model is constructed by combining the key driving scenario information that affects vehicle obstacle avoidance with the weight of the optimization function,and an anthropomorphic obstacle avoidance trajectory planning strategy for adaptive driving scenarios is proposed.Finally,the proposed strategy is verified based on real driving scenarios.The results show that the strategy can adjust the weight distribution of the trajectory optimization function in real time according to the“emergency degree”of obstacle avoidance and the state of the vehicle.Moreover,this strategy can generate anthropomorphic trajectories that are similar to expert-demonstrated trajectories,effectively improving the adaptability and acceptability of trajectories in driving scenarios.
基金supported by the National Natural Science Foundation of China(Grant Nos.41590845&41601096)the China Postdoctoral Science Foundation(Grant No.2015M581160)
文摘Abstract Cities based on coal resources have increasingly important social and economic roles in China. Their strategies for sustainable development, however, urgently need to be improved, which represents a huge challenge. Most observers believe that the continued progress of these cities relies on the optimization of scientific adaptive management in which social, economic, and ecological factors are incorporated. A systems perspective that combines policies, management priorities, and long-term policy impacts needs to be applied. To date, however, such an approach has not been adopted, which means it is difficult to implement adaptive management at the regional scale. In this study, we used various situations to develop a multiple adaptive scenario system dynamics model. We then simulated a range of policy scenarios, with Ordos in the Inner Mongolia Autonomous Region as a case study. Simulation results showed that the current strategy is not sustainable and predicted that the system would exceed the environmental capacity, with risks of resource exhaustion and urban decline in 2025-2035. Five critical policy variables, including the urban population carrying capacity, rates of water consumption and water recycling, and expansion of urban land cover, were identified during sensitivity analysis. We developed and compared six socio-economic scenarios. The urban area, represented by the urban population density, seemed to transition through five different stages, namely natural growth, rapid growth, stable oscillation, fading, and rebalancing. Our scenarios suggested that different policies had different roles through each stage. The water use efficiency management policy had a comprehensive far-reaching influence on the system behavior; land urbanization management functions dominated at the start, and population capacity management was a major control in the mid-term. Our results showed that the water recycling policy and the urban population carrying capacity were extremely important, and both should be reinforced and evaluated by the local governments.
