%0 Journal Article %1 Hart2021-mr %A Hart, Fabian %A Waltz, Martin %A Okhrin, Ostap %D 2021 %I arXiv %K %T Missing velocity in dynamic obstacle avoidance based on Deep Reinforcement Learning %X We introduce a novel approach to dynamic obstacle avoidance based on Deep Reinforcement Learning by defining a traffic type independent environment with variable complexity. Filling a gap in the current literature, we thoroughly investigate the effect of missing velocity information on an agent's performance in obstacle avoidance tasks. This is a crucial issue in practice since several sensors yield only positional information of objects or vehicles. We evaluate frequently-applied approaches in scenarios of partial observability, namely the incorporation of recurrency in the deep neural networks and simple frame-stacking. For our analysis, we rely on state-of-the-art model-free deep RL algorithms. The lack of velocity information is found to significantly impact the performance of an agent. Both approaches - recurrency and frame-stacking - cannot consistently replace missing velocity information in the observation space. However, in simplified scenarios, they can significantly boost performance and stabilize the overall training procedure.

@article{Hart2021-mr, abstract = {We introduce a novel approach to dynamic obstacle avoidance based on Deep Reinforcement Learning by defining a traffic type independent environment with variable complexity. Filling a gap in the current literature, we thoroughly investigate the effect of missing velocity information on an agent's performance in obstacle avoidance tasks. This is a crucial issue in practice since several sensors yield only positional information of objects or vehicles. We evaluate frequently-applied approaches in scenarios of partial observability, namely the incorporation of recurrency in the deep neural networks and simple frame-stacking. For our analysis, we rely on state-of-the-art model-free deep RL algorithms. The lack of velocity information is found to significantly impact the performance of an agent. Both approaches - recurrency and frame-stacking - cannot consistently replace missing velocity information in the observation space. However, in simplified scenarios, they can significantly boost performance and stabilize the overall training procedure.}, added-at = {2024-09-10T11:56:37.000+0200}, author = {Hart, Fabian and Waltz, Martin and Okhrin, Ostap}, biburl = {https://puma.scadsai.uni-leipzig.de/bibtex/2951c2fe6cc1ef3e28f8391f399f6454c/scadsfct}, interhash = {870622ce0146b65d832f762b4e290a19}, intrahash = {951c2fe6cc1ef3e28f8391f399f6454c}, keywords = {}, publisher = {arXiv}, timestamp = {2024-09-10T15:15:57.000+0200}, title = {Missing velocity in dynamic obstacle avoidance based on Deep Reinforcement Learning}, year = 2021 }