HyPlan: Hybrid Learning-Assisted Planning Under Uncertainty for Safe Autonomous Driving
This work addresses the problem of safe and efficient autonomous driving in uncertain traffic scenarios, but it appears incremental as it builds on existing methods like POMDP planning and reinforcement learning.
The paper tackles collision-free navigation for self-driving cars in partially observable traffic environments by proposing HyPlan, a hybrid learning-assisted planning method that combines behavior prediction, deep reinforcement learning, and approximated POMDP planning. The result shows that HyPlan navigates safer than selected baselines and performs significantly faster than alternative online POMDP planners in experiments on the CARLA-CTS2 benchmark.
We present a novel hybrid learning-assisted planning method, named HyPlan, for solving the collision-free navigation problem for self-driving cars in partially observable traffic environments. HyPlan combines methods for multi-agent behavior prediction, deep reinforcement learning with proximal policy optimization and approximated online POMDP planning with heuristic confidence-based vertical pruning to reduce its execution time without compromising safety of driving. Our experimental performance analysis on the CARLA-CTS2 benchmark of critical traffic scenarios with pedestrians revealed that HyPlan may navigate safer than selected relevant baselines and perform significantly faster than considered alternative online POMDP planners.