Robust Navigation with Cross-Modal Fusion and Knowledge Transfer

TL;DR

This paper introduces a cross-modal fusion and knowledge transfer framework using teacher-student distillation to enhance the generalization and sim-to-real transfer of navigation skills in mobile robots, demonstrating significant improvements in robustness.

Contribution

It proposes a novel teacher-student distillation approach with cross-modal fusion for improved navigation generalization and sim-to-real transfer.

Findings

Outperforms baseline methods significantly in experiments.

Achieves robust navigation under varying conditions.

Effective in both simulated and real-world environments.

Abstract

Recently, learning-based approaches show promising results in navigation tasks. However, the poor generalization capability and the simulation-reality gap prevent a wide range of applications. We consider the problem of improving the generalization of mobile robots and achieving sim-to-real transfer for navigation skills. To that end, we propose a cross-modal fusion method and a knowledge transfer framework for better generalization. This is realized by a teacher-student distillation architecture. The teacher learns a discriminative representation and the near-perfect policy in an ideal environment. By imitating the behavior and representation of the teacher, the student is able to align the features from noisy multi-modal input and reduce the influence of variations on navigation policy. We evaluate our method in simulated and real-world environments. Experiments show that our method outperforms the baselines by a large margin and achieves robust navigation performance with varying working conditions.