Authors:
Chinnawut Nantabut
and
Dirk Abel
Affiliation:
Institute of Automatic Control, RWTH Aachen University, Campus Boulevard 30, Aachen 52074, Germany
Keyword(s):
Collision Avoidance, Autonomous Driving, Path Planning, Trajectory Planning, Object Detection, L-Shape Fitting, Hybrid A*, Weighted A*, Stanley Controller, PID Controller, Bicycle Reciprocal Collision Avoidance.
Abstract:
In the research field of autonomous driving, planning safe and effective trajectories is a key issue, which also requires reliable detection of objects in the environment. This publication introduces a new approach to compute safe trajectories for automated road vehicles quickly and robustly, also considering reliable object detection for static and dynamic objects. For this purpose, the Hybrid A* algorithm modified with Weighted A* is used to accelerate the planning of a collision-free path because the weight w can make the heuristic term h become more important and make the tree much more narrow in the direction of the goal. Afterwards, PID- as well as Stanley controllers are utilized to realize reliable trajectories. This combined algorithm is extended with the L-Shape fitting algorithm to detect objects in the environment. The entire approach is evaluated for unstructured and semistructured environments using simulations of an automated vehicle with a realistic interaction of dyn
amic obstacles in the presence of model and sensor uncertainties, guarantees a real-time capability of 1 s, and results in collision-free vehicle movement. The whole algorithm, which yields very promising results, will be transferred to a C++ framework and tested with flexible test vehicles in real environments in the future.
(More)