Context-Conditional Navigation with a Learning-Based Terrain- and Robot-Aware Dynamics Model

TL;DR

This paper introduces TRADYN, a probabilistic, adaptive dynamics model for autonomous navigation that accounts for terrain and robot variations, improving long-term prediction and planning in dynamic environments.

Contribution

The paper presents TRADYN, a novel meta-learning based dynamics model that adapts to terrain and robot changes, enhancing navigation accuracy and planning efficiency.

Findings

Lower prediction error in long-horizon trajectory tasks.

Improved navigation planning performance.

Effective adaptation to terrain and robot variations.

Abstract

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.