2020 · 129 citations · 21 references
ComputingAutonomous SystemsComputer ScienceMachine LearningMotion PlanningRoboticsAutonomous NavigationImitation LearningObstacle AvoidanceReinforcement LearningRobot Motion PlanningRobot NavigationDeep Reinforcement LearningDeep Reinforcement Learning For NavigationLearning By ImitationMobile Robot NavigationNavigation In Cluttered EnvironmentsReinforcement Learning For NavigationSafe Motion PlanningSimulated Environments
Mobile robots operating in public environments require the ability to navigate among humans and other obstacles in a socially compliant and safe manner. The study proposes a combined imitation learning and deep reinforcement learning method for motion planning in crowded and cluttered environments. The approach processes static and dynamic object information separately, enabling the network to learn motion patterns tailored to real-world settings and to function with limited sensor field of view. The model outperforms state‑of‑the‑art methods in simulated environments with human‑like agents and static obstacles, and it demonstrates real‑time performance by successfully navigating a robotic platform in real‑world settings.
Mobile robots operating in public environments require the ability to navigate among humans and other obstacles in a socially compliant and safe manner. This work presents a combined imitation learning and deep reinforcement learning approach for motion planning in such crowded and cluttered environments. By separately processing information related to static and dynamic objects, we enable our network to learn motion patterns that are tailored to real-world environments. Our model is also designed such that it can handle usual cases in which robots can be equipped with sensor suites that only offer limited field of view. Our model outperforms current state-of-the-art approaches, which is shown in simulated environments containing human-like agents and static obstacles. Additionally, we demonstrate the real-time performance and applicability of our model by successfully navigating a robotic platform through real-world environments.
21
Adam: A Method for Stochastic Optimization
Diederik P. Kingma, Jimmy Ba · UvA-DARE (University of Amsterdam) · 2014 · 84.8K citations · Full text
You'll never walk alone: Modeling social behavior for multi-target tracking
S. Pellegrini, Andreas Ess, Konrad Schindler et al. · 2009 · 1.6K citations