Learning-on-the-Drive: Self-supervised Adaptation of Visual Offroad Traversability Models
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2023
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916435625771008 |
|---|---|
| author | Chen, Eric Ho, Cherie Maulimov, Mukhtar Wang, Chen Scherer, Sebastian |
| author_facet | Chen, Eric Ho, Cherie Maulimov, Mukhtar Wang, Chen Scherer, Sebastian |
| contents | Autonomous offroad driving is essential for applications like emergency rescue, military operations, and agriculture. Despite progress, systems struggle with high-speed vehicles exceeding 10m/s due to the need for accurate long-range (> 50m) perception for safe navigation. Current approaches are limited by sensor constraints; LiDAR-based methods offer precise short-range data but are noisy beyond 30m, while visual models provide dense long-range measurements but falter with unseen scenarios. To overcome these issues, we introduce ALTER, a learning-on-the-drive perception framework that leverages both sensor types. ALTER uses a self-supervised visual model to learn and adapt from near-range LiDAR measurements, improving long-range prediction in new environments without manual labeling. It also includes a model selection module for better sensor failure response and adaptability to known environments. Testing in two real-world settings showed on average 43.4% better traversability prediction than LiDAR-only and 164% over non-adaptive state-of-the-art (SOTA) visual semantic methods after 45 seconds of online learning. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2306_15226 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Learning-on-the-Drive: Self-supervised Adaptation of Visual Offroad Traversability Models Chen, Eric Ho, Cherie Maulimov, Mukhtar Wang, Chen Scherer, Sebastian Robotics Autonomous offroad driving is essential for applications like emergency rescue, military operations, and agriculture. Despite progress, systems struggle with high-speed vehicles exceeding 10m/s due to the need for accurate long-range (> 50m) perception for safe navigation. Current approaches are limited by sensor constraints; LiDAR-based methods offer precise short-range data but are noisy beyond 30m, while visual models provide dense long-range measurements but falter with unseen scenarios. To overcome these issues, we introduce ALTER, a learning-on-the-drive perception framework that leverages both sensor types. ALTER uses a self-supervised visual model to learn and adapt from near-range LiDAR measurements, improving long-range prediction in new environments without manual labeling. It also includes a model selection module for better sensor failure response and adaptability to known environments. Testing in two real-world settings showed on average 43.4% better traversability prediction than LiDAR-only and 164% over non-adaptive state-of-the-art (SOTA) visual semantic methods after 45 seconds of online learning. |
| title | Learning-on-the-Drive: Self-supervised Adaptation of Visual Offroad Traversability Models |
| topic | Robotics |
| url | https://arxiv.org/abs/2306.15226 |