Risk-Based Filtering of Valuable Driving Situations in the Waymo Open Motion Dataset
Fuente:
arXiv
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866909666704883712 |
|---|---|
| author | Puphal, Tim Ramtekkar, Vipul Nishimiya, Kenji |
| author_facet | Puphal, Tim Ramtekkar, Vipul Nishimiya, Kenji |
| contents | Improving automated vehicle software requires driving data rich in valuable road user interactions. In this paper, we propose a risk-based filtering approach that helps identify such valuable driving situations from large datasets. Specifically, we use a probabilistic risk model to detect high-risk situations. Our method stands out by considering a) first-order situations (where one vehicle directly influences another and induces risk) and b) second-order situations (where influence propagates through an intermediary vehicle). In experiments, we show that our approach effectively selects valuable driving situations in the Waymo Open Motion Dataset. Compared to the two baseline interaction metrics of Kalman difficulty and Tracks-To-Predict (TTP), our filtering approach identifies complex and complementary situations, enriching the quality in automated vehicle testing. The risk data is made open-source: https://github.com/HRI-EU/RiskBasedFiltering. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_23433 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Risk-Based Filtering of Valuable Driving Situations in the Waymo Open Motion Dataset Puphal, Tim Ramtekkar, Vipul Nishimiya, Kenji Robotics Improving automated vehicle software requires driving data rich in valuable road user interactions. In this paper, we propose a risk-based filtering approach that helps identify such valuable driving situations from large datasets. Specifically, we use a probabilistic risk model to detect high-risk situations. Our method stands out by considering a) first-order situations (where one vehicle directly influences another and induces risk) and b) second-order situations (where influence propagates through an intermediary vehicle). In experiments, we show that our approach effectively selects valuable driving situations in the Waymo Open Motion Dataset. Compared to the two baseline interaction metrics of Kalman difficulty and Tracks-To-Predict (TTP), our filtering approach identifies complex and complementary situations, enriching the quality in automated vehicle testing. The risk data is made open-source: https://github.com/HRI-EU/RiskBasedFiltering. |
| title | Risk-Based Filtering of Valuable Driving Situations in the Waymo Open Motion Dataset |
| topic | Robotics |
| url | https://arxiv.org/abs/2506.23433 |