Deep Deterministic Policy Gradient-Based Autonomous Driving for Mobile Robots in Sparse Reward Environments.
Minjae ParkSeok Young LeeJin Seok HongNam Kyu KwonPublished in: Sensors (2022)
Keyphrases
- mobile robot
- autonomous driving
- dynamic environments
- unstructured environments
- autonomous robots
- initially unknown
- grand challenge
- reward function
- path planning
- robotic systems
- reinforcement learning
- optimal policy
- obstacle avoidance
- control policy
- average reward
- policy gradient
- expected reward
- stereo vision
- inverse reinforcement learning
- motion planning
- markov decision processes
- stationary policies
- urban traffic
- multi robot
- high quality
- long run