aiqbench analysis
The paper uses a learned, end-to-end planner that forecasts occupancy and predicts a distribution over clearance, trained with a risk cost tied to observed collisions. Its central contribution is a learning method for uncertainty-aware control, not just a robotics system. Readers should note that the evidence is closed-loop simulation with up to 45 pedestrians, so real-world transfer and sensor-noise robustness remain open questions.
Don't Risk It!: Trajectory-Conditioned Distributional Risk for LiDAR-Only Crowd Navigation
arXiv:2610.40050v1 Announce Type: new Abstract: Efficient crowd navigation requires anticipating dynamic collision-free space without relying on fragile object tracking. We propose the Don't Risk It Planner (DRIP), an end-to-end LiDAR-only planning framework that couples occupancy forecasting with trajectory-conditioned clearance and uncertainty estimation. Operating directly on LiDAR-derived occupancy grid histories, DRIP predicts a distribution over minimum robot-obstacle clearance for candidate control sequences to evaluate collision risk. The model is trained using a risk cost that grounds predictive uncertainty directly in empirical collision outcomes rather than geometric regression alone. In closed-loop experiments with up to 45 pedestrians, DRIP achieves higher success rates with fewer collisions and reduced freezing behavior compared to state-of-the-art baselines.
Title:Don't Risk It!: Trajectory-Conditioned Distributional Risk for LiDAR-Only Crowd Navigation
Abstract:Efficient crowd navigation requires anticipating dynamic collision-free space without relying on fragile object tracking. We propose the Don't Risk It Planner (DRIP), an end-to-end LiDAR-only planning framework that couples occupancy forecasting with trajectory-conditioned clearance and uncertainty estimation. Operating directly on LiDAR-derived occupancy grid histories, DRIP predicts a distribution over minimum robot-obstacle clearance for candidate control sequences to evaluate collision risk. The model is trained using a risk cost that grounds predictive uncertainty directly in empirical collision outcomes rather than geometric regression alone. In closed-loop experiments with up to 45 pedestrians, DRIP achieves higher success rates with fewer collisions and reduced freezing behavior compared to state-of-the-art baselines.
Robotics (cs.RO)
arXiv:2610.40050 [cs.RO]
(or arXiv:2610.40050v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.40050 Focus to learn more arXiv-issued DOI via DataCite
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 207 words