Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Learning Material-Aware Hamiltonian Risk Fields for Safe Navigation

About

Risk-aware navigation should be selective: a policy should expose evasive degrees of freedom only when the local scene admits a lower-risk feasible maneuver, and suppress them when no safer alternative exists. We show that adding one context-energy term to a port-Hamiltonian navigation policy produces a learned force channel with exactly this falsifiable signature. When the local risk field contains a feasible lower-risk direction, the induced context force activates toward it; when the apparent escape is blocked or not yet available, a route-aware gate suppresses lateral force rather than hallucinating an unsafe maneuver. A CVaR tail-risk objective focuses gradient updates on rare but consequential risk transitions. We validate the selectivity signature across four settings. In the primary delayed-required-escape benchmark, route-aware CVaR reduces premature force activation from 0.950 to 0.180 versus DWA while raising success from 0.480 to 0.810 with zero replans. On real off-road terrain (RELLIS-3D), route-aware enrichment achieves correct activation rate 0.837 and false activation rate 0.114, compared to 0.378/0.752 for scalar risk gradients. On static semantic maps (DFC2018), enrichment reduces catastrophic failure from 0.60 to 0.10 and oscillation by 90.7% while preserving path efficiency. In highway traffic, collisions drop from 100% to 0% when a lane escape is feasible; when no escape exists, the policy suppresses the lateral maneuver. The selectivity property follows from the gradient structure of the context energy rather than from training-time tuning.

Aditya Sai Ellendula, Yi Wang, Chandrajit Bajaj• 2026

Related benchmarks

TaskDatasetResultRank
NavigationRELLIS-Dyn 3-event material aggregate
Success Rate100
11
Highway NavigationHighway Mean over three scenarios 200 seeds each (test)
Success Rate100
9
Navigation PlanningDFC episodes 2018 (test)
Success Rate100
9
Delayed Required EscapeRELLIS-Dyn Delayed-required-escape scenario
False Pre-activation0.00e+0
8
Spatial SelectivityRELLIS-3D (leave-one-sequence-out)
CAR88.4
6
Spatial SelectivityRELLIS-3D (five leave-one-sequence-out splits)
CAR88.4
6
Showing 6 of 6 rows

Other info

Follow for update