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

by   Suresh Guttikonda, et al.

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.


page 1

page 4

page 5

page 6


Deep Reinforcement Learning with Successor Features for Navigation across Similar Environments

In this paper we consider the problem of robot navigation in simple maze...

Personalized Dynamics Models for Adaptive Assistive Navigation Interfaces

We explore the role of personalization for assistive navigational system...

Generating Robust Supervision for Learning-Based Visual Navigation Using Hamilton-Jacobi Reachability

In Bansal et al. (2019), a novel visual navigation framework that combin...

Tracking and Planning with Spatial World Models

We introduce a method for real-time navigation and tracking with differe...

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Learning is an inherently continuous phenomenon. When humans learn a new...

Probabilistic Traversability Model for Risk-Aware Motion Planning in Off-Road Environments

A key challenge in off-road navigation is that even visually similar or ...

Please sign up or login with your details

Forgot password? Click here to reset