Online Risk-Bounded Motion Planning for Autonomous Vehicles in Dynamic Environments
This addresses the problem of safe and efficient navigation for autonomous vehicles in dynamic settings, though it is incremental as it builds on existing POMDP and intent recognition methods.
The paper tackles motion planning for autonomous vehicles in dynamic environments by modeling it as a POMDP and combining intent recognition with a solver to generate risk-bounded plans, demonstrating improved efficiency and safety in scenarios like unprotected left turns and lane changes compared to baselines.
A crucial challenge to efficient and robust motion planning for autonomous vehicles is understanding the intentions of the surrounding agents. Ignoring the intentions of the other agents in dynamic environments can lead to risky or over-conservative plans. In this work, we model the motion planning problem as a partially observable Markov decision process (POMDP) and propose an online system that combines an intent recognition algorithm and a POMDP solver to generate risk-bounded plans for the ego vehicle navigating with a number of dynamic agent vehicles. The intent recognition algorithm predicts the probabilistic hybrid motion states of each agent vehicle over a finite horizon using Bayesian filtering and a library of pre-learned maneuver motion models. We update the POMDP model with the intent recognition results in real time and solve it using a heuristic search algorithm which produces policies with upper-bound guarantees on the probability of near colliding with other dynamic agents. We demonstrate that our system is able to generate better motion plans in terms of efficiency and safety in a number of challenging environments including unprotected intersection left turns and lane changes as compared to the baseline methods.