Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model
This work addresses the challenge of adapting to environmental and system variations in autonomous robots, though it appears incremental as it builds on existing meta-learning methods.
The paper tackles the problem of autonomous navigation under varying terrain and robot dynamics by developing a probabilistic, terrain- and robot-aware forward dynamics model called TRADYN, which shows lower prediction error for long-horizon trajectory prediction and improved performance in navigation planning compared to non-adaptive models.
In autonomous navigation settings, several quantities can be subject to variations. Terrain properties such as friction coefficients may vary over time depending on the location of the robot. Also, the dynamics of the robot may change due to, e.g., different payloads, changing the system's mass, or wear and tear, changing actuator gains or joint friction. An autonomous agent should thus be able to adapt to such variations. In this paper, we develop a novel probabilistic, terrain- and robot-aware forward dynamics model, termed TRADYN, which is able to adapt to the above-mentioned variations. It builds on recent advances in meta-learning forward dynamics models based on Neural Processes. We evaluate our method in a simulated 2D navigation setting with a unicycle-like robot and different terrain layouts with spatially varying friction coefficients. In our experiments, the proposed model exhibits lower prediction error for the task of long-horizon trajectory prediction, compared to non-adaptive ablation models. We also evaluate our model on the downstream task of navigation planning, which demonstrates improved performance in planning control-efficient paths by taking robot and terrain properties into account.