Geographically disparate sensor fusion for enhanced target detection and identification in autonomous vehicles
Examples disclosed herein relate to an autonomous driving system in an ego vehicle. The autonomous driving system includes a radar system configured to detect and identify a target in a path and a surrounding environment of the ego vehicle. The autonomous driving system also includes a sensor fusion module configured to receive radar data on the identified target from the radar system and compare the identified target with one or more targets identified by a plurality of perception sensors that are geographically disparate from the radar system. Other examples disclosed herein include a method of operating the radar system in the autonomous driving system of the ego vehicle.
1 . An autonomous control system, comprising:
a radar module;
a computer processing unit;
a memory storage device;
wherein the computer processing unit is configured to:
receive sensor information from a plurality of sensors, the plurality of sensors including the radar module,
detect and identify targets and determine control actions for the autonomous control system based on the sensor information, wherein the computer processing unit utilizes one or more deep learning networks that are trained with the radar data and the sensor data for target identification;
track targets from sensor information based on a target list and occupancy map, wherein to track targets over time the computer processing unit utilizes a Kalman filter and combining sensor information from at least one previous timeframe with the sensor information from the plurality of sensors; and
store information describing a field of view of the plurality of sensors in a composite data repository; and
a communication bus coupled to the computer processing unit the radar module and the plurality of sensors.
2 . The autonomous control system of claim 1 , wherein the radar module comprises an antenna structure configured to generate and steer one or more transmission RF beams and receive one or more return RF beams reflected from the surrounding environment.
3 . The autonomous control system of claim 1 , wherein the autonomous control system is adapted to control a vehicle.
4 . The autonomous control system as in claim 3 , wherein the computer processing unit is configured to combine data from different perception sensors in the vehicle and data received from sensors in other geographically disparate vehicles to perceive an environment.
5 . The autonomous control system as in claim 4 , wherein the computer processing unit is configured to send a control signal to at least one of the plurality of sensors based on historical sensor data from the radar module.
6 . The autonomous control system as in claim 5 , wherein the radar module comprises an antenna array and the control signal controls directionality of one or more antenna cells in the antenna array.
7 . The autonomous control system of claim 6 , wherein the control signal comprises an instruction to the antenna array to radiate transmission RF beams at a first phase shift and direction within at least a portion of the field of view corresponding to a location of a target identified by the radar system.
8 . The autonomous control system of claim 1 , wherein the computer processing unit is adapted to receive information from sensor fusion modules in other autonomous control systems.
9 . The autonomous control system of claim 8 , wherein the received information from other autonomous control systems includes time stamps indicating a time of data collection and a location information.
10 . The autonomous control system of claim 9 , wherein the computer processing unit is adapted to receive mapping information for application to sensor information.
11 . The autonomous control system of claim 10 , wherein the mapping information is used to track targets.
12 . The autonomous control system of claim 11 , wherein the computer processing unit is configured to generate target identification information based on tracking information.
13 . The autonomous control system as in claim 1 , further comprising:
a transceiver adapted to receive communications from other vehicles and infrastructure components.
14 . A vehicle to vehicle (V2V) communication system in a vehicle, comprising:
a computer processing unit, wherein the computer processing unit is configured to:
receive information from vehicles, the information comprises sensor information from one or more sensors of the vehicles,
detect and identify targets and determine control actions for the autonomous control system based on the sensor information, wherein the computer processing unit utilizes one or more deep learning networks that are trained with radar data and sensor data for target identification, and
track targets from sensor information based on a target list and occupancy map, wherein to track targets over time the computer processing unit utilizes a Kalman filter and combining sensor information from at least one previous timeframe with the sensor information from the plurality of sensors; and
a communication bus for communication with modules within the vehicle.
15 . The V2V communication system as in claim 14 , wherein the information is from a lead vehicle in a path of the vehicle.
16 . The V2V communication system as in claim 15 , further comprising a radar module adapted to provide range Doppler maps (RDM) to the computer processing unit.
17 . The V2V communication system as in claim 16 , wherein the computer processing unit receives point cloud data corresponding to the information and combining with RDM data from the radar module.
18 . The V2V communication system as in claim 17 , wherein the information provided to the computer processing unit is adapted to provide control decisions to avoid an accident.
19 . The V2V communication system as in claim 14 , wherein the information includes communications related to weather conditions in the environment.