StratXplore: Strategic Novelty-seeking and Instruction-aligned Exploration for Vision and Language Navigation

TL;DR

StratXplore introduces a memory-based, mistake-aware exploration strategy for vision-language navigation, enabling robots to better recover from errors by selecting optimal unexplored viewpoints aligned with instructions.

Contribution

The paper proposes a novel exploration method that leverages memory and mistake-awareness to improve navigation success in VLN tasks.

Findings

Improved success rates on VLN datasets.

Effective recovery from navigational mistakes.

Enhanced decision-making with exploration of unexplored frontiers.

Abstract

Embodied navigation requires robots to understand and interact with the environment based on given tasks. Vision-Language Navigation (VLN) is an embodied navigation task, where a robot navigates within a previously seen and unseen environment, based on linguistic instruction and visual inputs. VLN agents need access to both local and global action spaces; former for immediate decision making and the latter for recovering from navigational mistakes. Prior VLN agents rely only on instruction-viewpoint alignment for local and global decision making and back-track to a previously visited viewpoint, if the instruction and its current viewpoint mismatches. These methods are prone to mistakes, due to the complexity of the instruction and partial observability of the environment. We posit that, back-tracking is sub-optimal and agent that is aware of its mistakes can recover efficiently. For optimal recovery, exploration should be extended to unexplored viewpoints (or frontiers). The optimal frontier is a recently observed but unexplored viewpoint that aligns with the instruction and is novel. We introduce a memory-based and mistake-aware path planning strategy for VLN agents, called \textit{StratXplore}, that presents global and local action planning to select the optimal frontier for path correction. The proposed method collects all past actions and viewpoint features during navigation and then selects the optimal frontier suitable for recovery. Experimental results show this simple yet effective strategy improves the success rate on two VLN datasets with different task complexities.