Learning Vision-Guided Dynamic Locomotion Over Challenging Terrains
This work addresses mobility challenges for legged robots in rough environments, representing an incremental improvement in perceptual locomotion.
The paper tackles the problem of enabling legged robots to navigate challenging terrains using a deep reinforcement learning approach with a novel Dynamic Reward Strategy, achieving over 90% success rates in tests.
Legged robots are becoming increasingly powerful and popular in recent years for their potential to bring the mobility of autonomous agents to the next level. This work presents a deep reinforcement learning approach that learns a robust Lidar-based perceptual locomotion policy in a partially observable environment using Proximal Policy Optimisation. Visual perception is critical to actively overcome challenging terrains, and to do so, we propose a novel learning strategy: Dynamic Reward Strategy (DRS), which serves as effective heuristics to learn a versatile gait using a neural network architecture without the need to access the history data. Moreover, in a modified version of the OpenAI gym environment, the proposed work is evaluated with scores over 90% success rate in all tested challenging terrains.