Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2412.17282 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912166576128000 |
|---|---|
| author | Uemura, Riku Tanaka, Kanji Tsukahara, Kenta Iwata, Daiki |
| author_facet | Uemura, Riku Tanaka, Kanji Tsukahara, Kenta Iwata, Daiki |
| contents | Point goal navigation (PGN) is a mapless navigation approach that trains robots to visually navigate to goal points without relying on pre-built maps. Despite significant progress in handling complex environments using deep reinforcement learning, current PGN methods are designed for single-robot systems, limiting their generalizability to multi-robot scenarios with diverse platforms. This paper addresses this limitation by proposing a knowledge transfer framework for PGN, allowing a teacher robot to transfer its learned navigation model to student robots, including those with unknown or black-box platforms. We introduce a novel knowledge distillation (KD) framework that transfers first-person-view (FPV) representations (view images, turning/forward actions) to universally applicable third-person-view (TPV) representations (local maps, subgoals). The state is redefined as reconstructed local maps using SLAM, while actions are mapped to subgoals on a predefined grid. To enhance training efficiency, we propose a sampling-efficient KD approach that aligns training episodes via a noise-robust local map descriptor (LMD). Although validated on 2D wheeled robots, this method can be extended to 3D action spaces, such as drones. Experiments conducted in Habitat-Sim demonstrate the feasibility of the proposed framework, requiring minimal implementation effort. This study highlights the potential for scalable and cross-platform PGN solutions, expanding the applicability of embodied AI systems in multi-robot scenarios. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2412_17282 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | LMD-PGN: Cross-Modal Knowledge Distillation from First-Person-View Images to Third-Person-View BEV Maps for Universal Point Goal Navigation Uemura, Riku Tanaka, Kanji Tsukahara, Kenta Iwata, Daiki Robotics Point goal navigation (PGN) is a mapless navigation approach that trains robots to visually navigate to goal points without relying on pre-built maps. Despite significant progress in handling complex environments using deep reinforcement learning, current PGN methods are designed for single-robot systems, limiting their generalizability to multi-robot scenarios with diverse platforms. This paper addresses this limitation by proposing a knowledge transfer framework for PGN, allowing a teacher robot to transfer its learned navigation model to student robots, including those with unknown or black-box platforms. We introduce a novel knowledge distillation (KD) framework that transfers first-person-view (FPV) representations (view images, turning/forward actions) to universally applicable third-person-view (TPV) representations (local maps, subgoals). The state is redefined as reconstructed local maps using SLAM, while actions are mapped to subgoals on a predefined grid. To enhance training efficiency, we propose a sampling-efficient KD approach that aligns training episodes via a noise-robust local map descriptor (LMD). Although validated on 2D wheeled robots, this method can be extended to 3D action spaces, such as drones. Experiments conducted in Habitat-Sim demonstrate the feasibility of the proposed framework, requiring minimal implementation effort. This study highlights the potential for scalable and cross-platform PGN solutions, expanding the applicability of embodied AI systems in multi-robot scenarios. |
| title | LMD-PGN: Cross-Modal Knowledge Distillation from First-Person-View Images to Third-Person-View BEV Maps for Universal Point Goal Navigation |
| topic | Robotics |
| url | https://arxiv.org/abs/2412.17282 |