PATH PREDICTION FOR A VEHICLE

• Main Authors: Mohammadiha, Nasser, Movert, Anders
• Format: Patent
• Language: English; French; German
• Published: 05.07.2023
• Subjects: BLASTING; CALCULATING; COMBUSTION ENGINES; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE ORDIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; CONTROLLING COMBUSTION ENGINES; COUNTING; HEATING; HOT-GAS OR COMBUSTION-PRODUCT ENGINE PLANTS; LIGHTING; MECHANICAL ENGINEERING; PERFORMING OPERATIONS; PHYSICS; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TOTHE CONTROL OF A PARTICULAR SUB-UNIT; TRANSPORTING; VEHICLES IN GENERAL; WEAPONS

The present invention relates to a method and a system (40) for predicting a near future path and an associated output control signal for a vehicle (1). For the prediction sensor data, vehicle driving data, and road data are collected. An input control signal indicative of an intended driving action is received (S608). The sensor data and the vehicle driving data is pre-processed (S610) to provide a set of object data comprising a time series of previous positions of the respective object relative the vehicle, a time series of the previous headings of the objects, and time series of previous velocities of the objects. The object data, the road data, the vehicle driving data, the control signal, and the sensor data is processed (S612) in a deep neural network. Based on the processing in the deep neural network, a predicted path output and an output control signal is provided (S614).