… Collisionavoidance algorithms are essential for safe and efficient robot operation among pedestrians. This work proposes using deep reinforcement (RL) learning … collisionavoidance …
P Long, T Fan, X Liao, W Liu… - 2018 IEEE international …, 2018 - ieeexplore.ieee.org
… To learn the optimal collisionavoidance policy, we propose a … policy gradient based reinforcementlearning algorithm trained … We demonstrate that the collisionavoidance policy …
… real-time implementable) interaction rule by learning a value function that implicitly encodes … collisionavoidance algorithm based on a novel application of deep reinforcementlearning, (…
… of solving collisionavoidance problems with the help of deep reinforcementlearning in an … whether a deep reinforcementlearning-based collisionavoidance method is superior to the …
… the collision risk. In this study, we proposed a collisionavoidance method that quantitatively assesses the collision risk and then generates an avoidance path. First, to assess the …
… In this paper, a deep reinforcementlearning (DRL)-based collisionavoidance method is … making stage of collisionavoidance, which determines whether the avoidance is necessary, …
D Wang, T Fan, T Han, J Pan - IEEE Robotics and Automation …, 2020 - ieeexplore.ieee.org
… to follow the well-known reciprocal collisionavoidance strategy, which can optimize deep … a decentralized reinforcementlearning based policy for multi-UAV collisionavoidance …
S Ouahouah, M Bagaa… - IEEE Internet of …, 2021 - ieeexplore.ieee.org
… deep-reinforcement-learning (DRL)-based algorithms for avoidingcollisions while saving … The obtained results demonstrated the efficiency of these solutions for avoiding the collision …
A Rafiei, AO Fasakhodi, F Hajati - International journal of automotive …, 2022 - Springer
… pedestrian collisionavoidance based on deep reinforcementlearning. A deep Q networN (DQN) is designed to discover an optimal driving policy for pedestrian collisionavoidance in …