Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2605.21406 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866914583506059264 |
|---|---|
| author | Link, Maximilian Xu, Yingjie Hu, Yingbai Liu, Yinlong |
| author_facet | Link, Maximilian Xu, Yingjie Hu, Yingbai Liu, Yinlong |
| contents | We present MC-Risk, a planner-aligned, multi-component risk field on a bird's-eye-view grid that yields early, calibrated, and class-aware risk localization. MC-Risk linearly composes three interpretable modules: (i) a motorized-agent field that fuses a black-box multimodal trajectory predictor with an analytic Gaussian-torus construction whose lateral width grows with speed/curvature and whose height attenuates with look-ahead; (ii) a VRU risk field that replaces isotropic pedestrian blobs with a forward-biased anisotropic kernel aligned to heading and speed; and (iii) a road penalty field that exploits full HD-map topology, imposing an off-road penalty and lane-aware risk exposure for same/opposite directions. We conduct, to our knowledge, the first standardized quantitative evaluation of a risk-field formulation on RiskBench's collision subset. MC-Risk attains the best overall risk localization and the earliest hazard indication. Finally, we demonstrate a plug-and-play planning interface by using the field as an MPC cost density, enabling risk-aware trajectory generation without additional training. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_21406 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MC-Risk: Multi-Component Risk Fields for Risk Identification and Motion Planning Link, Maximilian Xu, Yingjie Hu, Yingbai Liu, Yinlong Robotics We present MC-Risk, a planner-aligned, multi-component risk field on a bird's-eye-view grid that yields early, calibrated, and class-aware risk localization. MC-Risk linearly composes three interpretable modules: (i) a motorized-agent field that fuses a black-box multimodal trajectory predictor with an analytic Gaussian-torus construction whose lateral width grows with speed/curvature and whose height attenuates with look-ahead; (ii) a VRU risk field that replaces isotropic pedestrian blobs with a forward-biased anisotropic kernel aligned to heading and speed; and (iii) a road penalty field that exploits full HD-map topology, imposing an off-road penalty and lane-aware risk exposure for same/opposite directions. We conduct, to our knowledge, the first standardized quantitative evaluation of a risk-field formulation on RiskBench's collision subset. MC-Risk attains the best overall risk localization and the earliest hazard indication. Finally, we demonstrate a plug-and-play planning interface by using the field as an MPC cost density, enabling risk-aware trajectory generation without additional training. |
| title | MC-Risk: Multi-Component Risk Fields for Risk Identification and Motion Planning |
| topic | Robotics |
| url | https://arxiv.org/abs/2605.21406 |