SRL-VIC: A Variable Stiffness-Based Safe Reinforcement Learning for Contact-Rich Robotic Tasks.
Heng ZhangGökhan SolakGustavo J. G. LahrArash AjoudaniPublished in: IEEE Robotics Autom. Lett. (2024)
Keyphrases
- robotic tasks
- reinforcement learning
- motion planning
- planning under uncertainty
- dynamic environments
- markov decision processes
- function approximation
- robotic systems
- contact force
- model free
- state space
- path planning
- machine learning
- optimal policy
- belief space
- learning algorithm
- orders of magnitude
- sufficient conditions
- multi agent
- image sequences
- real time