Unmanned aerial vehicles(UAVs)face the challenge of autonomous obstacle avoidance in complex,multi-obstacle environments.Behavior cloning offers a promising approach to rapidly acquire a learning policy from limited e...Unmanned aerial vehicles(UAVs)face the challenge of autonomous obstacle avoidance in complex,multi-obstacle environments.Behavior cloning offers a promising approach to rapidly acquire a learning policy from limited expert demonstrations.However,pure imitation learning inherently suffers from poor exploration and limited generalization,typically necessitating extensive datasets to train competent student policies.We utilize a cross-modal variational autoencoder(CM-VAE)to extract compact features from raw visual inputs and UAV states,which then feed into a policy network.We evaluated our approach in a simulated environment featuring a challenging circular trajectory with eight gate obstacles.The results demonstrate that the policy trained with pure behavior cloning consistently failed.In stark contrast,our DAgger-augmented behavior cloning method successfully traversed all gates without collision.Our findings confirm that DAgger effectively mitigates the shortcomings of behavior cloning,enabling the creation of reliable and sample-efficient navigation policies for UAVs.展开更多
Thirty-Six Stratagems is one of the most important military works of ancient China.As the name of the book,it totally includes 36 stratagems that can be used in many different fields such as military,business,and poli...Thirty-Six Stratagems is one of the most important military works of ancient China.As the name of the book,it totally includes 36 stratagems that can be used in many different fields such as military,business,and politics.Covering the dagger with a smile is one of the most common ones in these stratagems.At the same time,it is the most insidious one.As a kind of psychological tactic,it usually acts as the secret weapon of the weak.Though this stratagem should not be seen as a kind of predominant strategy,it is still worth being researched deeply,because knowing more about this psychological tactic will offer a good reference for the researchers of ancient art of war.展开更多
基金supported by the National Natural Science Foundation of China(No.62576349)。
文摘Unmanned aerial vehicles(UAVs)face the challenge of autonomous obstacle avoidance in complex,multi-obstacle environments.Behavior cloning offers a promising approach to rapidly acquire a learning policy from limited expert demonstrations.However,pure imitation learning inherently suffers from poor exploration and limited generalization,typically necessitating extensive datasets to train competent student policies.We utilize a cross-modal variational autoencoder(CM-VAE)to extract compact features from raw visual inputs and UAV states,which then feed into a policy network.We evaluated our approach in a simulated environment featuring a challenging circular trajectory with eight gate obstacles.The results demonstrate that the policy trained with pure behavior cloning consistently failed.In stark contrast,our DAgger-augmented behavior cloning method successfully traversed all gates without collision.Our findings confirm that DAgger effectively mitigates the shortcomings of behavior cloning,enabling the creation of reliable and sample-efficient navigation policies for UAVs.
文摘Thirty-Six Stratagems is one of the most important military works of ancient China.As the name of the book,it totally includes 36 stratagems that can be used in many different fields such as military,business,and politics.Covering the dagger with a smile is one of the most common ones in these stratagems.At the same time,it is the most insidious one.As a kind of psychological tactic,it usually acts as the secret weapon of the weak.Though this stratagem should not be seen as a kind of predominant strategy,it is still worth being researched deeply,because knowing more about this psychological tactic will offer a good reference for the researchers of ancient art of war.
