Learning Resilient Behaviors for Navigation Under Uncertainty

TL;DR

This paper introduces an uncertainty-aware navigation network trained with a temperature decay paradigm, enabling autonomous robots to learn resilient, adaptive behaviors in unseen uncertain environments, addressing safety and flexibility issues in real-world applications.

Contribution

The paper proposes a novel uncertainty-aware navigation network and a temperature decay training paradigm for resilient autonomous navigation in unknown environments.

Findings

Learns resilient behaviors in diverse environments

Generates adaptive trajectories based on environmental uncertainty

Improves training stability and efficiency

Abstract

Deep reinforcement learning has great potential to acquire complex, adaptive behaviors for autonomous agents automatically. However, the underlying neural network polices have not been widely deployed in real-world applications, especially in these safety-critical tasks (e.g., autonomous driving). One of the reasons is that the learned policy cannot perform flexible and resilient behaviors as traditional methods to adapt to diverse environments. In this paper, we consider the problem that a mobile robot learns adaptive and resilient behaviors for navigating in unseen uncertain environments while avoiding collisions. We present a novel approach for uncertainty-aware navigation by introducing an uncertainty-aware predictor to model the environmental uncertainty, and we propose a novel uncertainty-aware navigation network to learn resilient behaviors in the prior unknown environments. To train the proposed uncertainty-aware network more stably and efficiently, we present the temperature decay training paradigm, which balances exploration and exploitation during the training process. Our experimental evaluation demonstrates that our approach can learn resilient behaviors in diverse environments and generate adaptive trajectories according to environmental uncertainties.