Real-Time Trajectory Adaptation for Quadrupedal Locomotion using Deep Reinforcement Learning
Siddhant Gangapurwala,Mathieu Geisert,Romeo Orsolino,Maurice Fallon,Ioannis Havoutis,Siddhant Gangapurwala,Mathieu Geisert,Romeo Orsolino,Maurice Fallon,Ioannis Havoutis
We present a control architecture for real-time adaptation and tracking of trajectories generated using a terrain-aware trajectory optimization solver. This approach enables us to circumvent the computationally exhaustive task of online trajectory optimization, and further introduces a control solution robust to systems modeled with approximated dynamics. We train a policy using deep reinforcement...
