aiqbench analysis
This research introduces RiskFly, a novel one-stage flight planner that integrates spatio-temporal risk prediction directly into the planning loop using frustum-aligned observations. By supervising the model with privileged closest-point-of-approach data during training while discarding it at deployment, the system achieves map-free operation on resource-constrained platforms with improved success rates in dynamic environments. The approach advances machine learning for robotics by resolving the latency gap between reactive avoidance and proactive risk anticipation through differentiable representation supervision.
RiskFly: Frustum-Aligned Spatio-Temporal Risk Fields for One-Stage Agile Flight in Dynamic Clutter
arXiv:2610.04566v1 Announce Type: new Abstract: Agile flight in unknown, cluttered, and dynamic environments requires a planner that knows where and when danger will appear, not only that a trajectory is dangerous. One-stage learning-based planners trained with differentiable privileged costs are fast and expert-free, but the only signal reaching their encoder is a scalar trajectory cost with no spatial or temporal structure, so avoidance degrades into late reactive maneuvers. We present RiskFly, a one-stage planner that predicts risk in the same space in which it acts. A dual-stream observation pairs a short depth sequence with a frustum-aligned inverted spherical range-map sequence, whose angular cells match the end-state proposals one to one. An auxiliary head regresses a frustum-aligned spatio-temporal risk field, supervised by a privileged closest-point-of-approach (CPA) target. This self-predicted field is queried differentiably along the instantiated quintic trajectory at its own arrival times, and also enters the training objective, so representation supervision and planning gradients meet in a single space. Privileged signals are discarded at deployment, and the planner runs map-free from onboard depth and proprioception. Extensive simulation and zero-shot real-world flights on resource-constrained platforms show higher success rates at comparable end-to-end latency.
Abstract:Agile flight in unknown, cluttered, and dynamic environments requires a planner that knows where and when danger will appear, not only that a trajectory is dangerous. One-stage learning-based planners trained with differentiable privileged costs are fast and expert-free, but the only signal reaching their encoder is a scalar trajectory cost with no spatial or temporal structure, so avoidance degrades into late reactive maneuvers. We present RiskFly, a one-stage planner that predicts risk in the same space in which it acts. A dual-stream observation pairs a short depth sequence with a frustum-aligned inverted spherical range-map sequence, whose angular cells match the end-state proposals one to one. An auxiliary head regresses a frustum-aligned spatio-temporal risk field, supervised by a privileged closest-point-of-approach (CPA) target. This self-predicted field is queried differentiably along the instantiated quintic trajectory at its own arrival times, and also enters the training objective, so representation supervision and planning gradients meet in a single space. Privileged signals are discarded at deployment, and the planner runs map-free from onboard depth and proprioception. Extensive simulation and zero-shot real-world flights on resource-constrained platforms show higher success rates at comparable end-to-end latency.
Robotics (cs.RO)
arXiv:2610.04566 [cs.RO]
(or arXiv:2610.04566v1 [cs.RO] for this version)
https://doi.org/10.48550/arXiv.2610.04566 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
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 · 280 words
Related coverage
From Matching Models to Recruiting Agents: A Systematized Narrative Review of AI Recruitment Systems, Evaluation, and Governance
arXiv · Sep 7, 2026
Game Design Creativity evals
LessWrong · Oct 12, 2026
Triton-Based Optimization of Video Sparse Attention on ROCm
AMD · Jul 13, 2026
State of the Field: AI for Epistemics and Coordination
LessWrong · Oct 2, 2026