Bunyo Okumura

Challenges in Perception and Decision Making for Intelligent Automotive Vehicles: A Case Study

This paper overviews challenges in perception and decision making for intelligent, or highly automated, automotive vehicles. We illustrate our development of a complete perception and decision making system which addresses various challenges and propose an action planning method for highly automated vehicles which can merge into a roundabout. We use learning from demonstration to construct a classifier for high-level decision making, and develop a novel set of formulations that is suited to this challenging situation: multiple agents in a highly dynamic environment with interdependencies between agents, partial observability, and a limited amount of training data. Having limited amount of labeled training data is highly constraining, but a very real issue in real-world applications. We believe that our formulations are also well suited to other automated driving scenarios.

Detection and motion planning for roadside parked vehicles at long distance

Reliable long distance obstacle detection and motion planning is a key issue for modern intelligent vehicles, since it can help to make the decision early and design proper driving trajectory to avoid discomfort for the passengers caused by hard brake or sudden large lateral movement. Specifically, when there is vehicle parked on the roadside, we need to detect its position and pass it safely with proper distance without causing much disruption during driving. In this paper, we propose a method to detect roadside parked vehicles robustly and design a trajectory with proper lateral offset from the lane center for the host vehicle to safely pass by it. To successfully detect the roadside parked vehicles, we fuse the output from a long range lidar and radar. We pre-compute multiple path candidates with different lateral offset, and the path planner selects the most proper one based on the distance of the parked vehicle to the lane center. To deal with false alarms and missing detections, we apply temporal filtering to the detection output and history of the decision making. The speed control is carefully designed to ensure that the host vehicle passes the parked vehicle with a safe and comfortable speed. The implemented system was evaluated in numerous scenarios with vehicles parked on the roadside. The results show that the system effectively commands the host vehicle to pass by the parked vehicle safely and comfortably with proper distance and smooth trajectory.