Risk Density RRT: Planning in the Space of Probability
Organizations: Soft Robotics for Human Cooperation and Rehabilitation, Istituto Italiano di Tecnologia, Genova 16163, Italy · Department of Information Engineering and Centro di Ricerca “Enrico Piaggio”, University of Pisa, Pisa 56122, Italy
Abstract
Planning under uncertainty is a fundamental problem in robotics. While much of the literature seeks minimum-cost paths subject to probabilistic constraints, this paper instead considers collision probability, or risk classically defined as probability times severity, directly as the planning objective. We propose Risk Density RRT (RD-RRT), an extension of RRT for high-level planning in environments with deterministic and uncertain obstacles. RD-RRT builds on Risk Density, a functional that evaluates a continuous path as a whole and provides a tractable approximation of its collision probability. The framework also supports severity-weighted risk and a hybrid variant that adds a path-length penalty, balancing risk and geometric efficiency while regularizing exploration in low-density regions. We validate the method across a wide range of scenarios. The results show that RD-RRT consistently finds paths with lower estimated collision probability by optimizing a global risk-based objective. We further demonstrate the fidelity of the underlying approximation through Monte Carlo simulations. Finally, we discuss how the topological structure induced by Risk Density may provide a useful representation of the environment and offer insights into risk-aware planning.
Figures & tables
| Category | Assumption |
|---|---|
| Space | The task space maps directly to the Configuration Space (Euclidean). No complex manifold constraints are considered. |
| Dynamics | The system is purely kinematic with no dynamic constraints. |
| Obstacles | Obstacles are outer-bounded by balls. |
| Independence | Obstacle distributions are conditionally independent of each other Eq. 22 . |
| Distributions | Uncertainty distributions must belong to a stable family (e.g., Gaussian, Cauchy). |
| Robot State | Robot position uncertainty is considered negligible and is ignored during planning. |
| 0.2 | 0.25 | 0.3 | 0.35 | |
|---|---|---|---|---|
| Eq. 28 | 0.853 | 0.971 | 1.045 | 1.104 |
| (H2) [%] | 63.80 | 68.99 | 71.96 | 74.27 |
| (H3) [%] | 63.81 | 69.04 | 71.99 | 74.28 |
| Length | 12.23 | 11.37 | 11.02 | 10.75 |
Appendix figures & tables4 assets
Supplementary material from the paper’s appendix.