Authors:
Johannes Wallner
;
Tito Tang
and
Markus Lienkamp
Affiliation:
Technische Universität München, Germany
Keyword(s):
Emergency Braking System, Teleoperated Vehicles, Lidar Sensor Raw Data, Particle Filter, Motion Prediction.
Related
Ontology
Subjects/Areas/Topics:
Informatics in Control, Automation and Robotics
;
Robotics and Automation
;
Telerobotics and Teleoperation
;
Vehicle Control Applications
Abstract:
A lidar-based approach of an emergency braking system for teleoperated vehicles is presented. Despite the time delay for the communication link of a teleoperated system, the vehicle has to be able to react to emerging objects in time. Starting with intelligent sensor data processing, reliable information is computed. An adapted particle filter algorithm tracks moving points to calculate their mean velocity, used for the prediction of surrounding moving objects. Further, in order to interpret this information, a situation assessment based on an intervention concept derived from Kamm’s circle is implemented. A motion prediction of possible trajectories of the ego-vehicle results in a clear decision-making process. All calculations are made at the raw data level and can be done online. Through artificial objects being included in real sensor data, the methodology was validated.