Exploiting Intrinsic Stochasticity of Real-Time Simulation to Facilitate Robust Reinforcement Learning for Robot Manipulation.
Ram DershanAmir M. Soufi EnayatiZengjie ZhangDean RichertHomayoun NajjaranPublished in: CoRR (2023)
Keyphrases
- real time
- reinforcement learning
- real robot
- real environment
- mobile robot
- vision system
- manipulation tasks
- simulated robot
- experimental platform
- robotic control
- high fidelity
- haptic feedback
- low cost
- state space
- simulation model
- multi robot
- mobile robot localization
- dynamic programming
- control system
- driver assistance systems
- autonomous mobile
- visual feedback
- obstacle avoidance
- robot navigation
- autonomous robots
- humanoid robot
- path planning
- control signals
- changing environment
- geometric structure