CeRLP: A Cross-embodiment Robot Local Planning Framework for Visual Navigation

TL;DR

CeRLP is a unified local planning framework for visual navigation across different robot types, using geometric abstraction and depth correction to improve obstacle avoidance and task success in diverse settings.

Contribution

The paper introduces CeRLP, a novel framework that generalizes visual navigation for heterogeneous robots by geometric abstraction and depth correction, reducing data needs and improving robustness.

Findings

Outperforms existing methods in simulation obstacle avoidance tasks.

Successfully generalizes to real-world point-to-point and vision-language navigation.

Demonstrates robustness across various robot and camera configurations.

Abstract

Visual navigation for cross-embodiment robots is challenging due to variations in robot and camera configurations, which can lead to the failure of navigation tasks. Previous approaches typically rely on collecting massive datasets across different robots, which is highly data-intensive, or fine-tuning models, which is time-consuming. Furthermore, both methods often lack explicit consideration of robot geometry. In this paper, we propose a Cross-embodiment Robot Local Planning (CeRLP) framework for general visual navigation, which abstracts visual information into a unified geometric formulation and applies to heterogeneous robots with varying physical dimensions, camera parameters, and camera types. CeRLP introduces a depth estimation scale correction method that utilizes offline pre-calibration to resolve the scale ambiguity of monocular depth estimation, thereby recovering precise metric depth images. Furthermore, CeRLP designs a visual-to-scan abstraction module that projects varying visual inputs into height-adaptive laser scans, making the policy robust to heterogeneous robots. Experiments in simulation environments demonstrate that CeRLP outperforms comparative methods, validating its robust obstacle avoidance capabilities as a local planner. Additionally, extensive real-world experiments verify the effectiveness of CeRLP in tasks such as point-to-point navigation and vision-language navigation, demonstrating its generalization across varying robot and camera configurations.