US 10,891,951 B2
Vehicle language processing
Lisa Scaria, Milpitas, CA (US); Praveen Narayanan, San Jose, CA (US); Francois Charette, Tracy, CA (US); and Ryan Burke, Palo Alto, CA (US)
Assigned to FORD GLOBAL TECHNOLOGIES, LLC, Dearborn, MI (US)
Filed by Ford Global Technologies, LLC, Dearborn, MI (US)
Filed on Oct. 17, 2018, as Appl. No. 16/162,556.
Prior Publication US 2020/0126544 A1, Apr. 23, 2020
Int. Cl. G10L 15/22 (2006.01); G10L 15/16 (2006.01); G10L 15/30 (2013.01); G10L 15/06 (2013.01); G06N 3/04 (2006.01)
CPC G10L 15/22 (2013.01) [G06N 3/0454 (2013.01); G10L 15/063 (2013.01); G10L 15/16 (2013.01); G10L 15/30 (2013.01); G10L 2015/223 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A method, comprising:
translating a spoken natural language command into an intermediate constructed language command with a first deep neural network;
determining a vehicle command and an intermediate constructed language response with a second deep neural network based on receiving vehicle information;
translating the intermediate constructed language response into a spoken natural language response with the third deep neural network; and
operating a vehicle based on the vehicle command;
wherein the first deep neural network, the second deep neural network and the third deep neural network are trained to input the spoken natural language command, output the vehicle command, input vehicle information and output the spoken natural language response using ground truth vehicle commands and vehicle information, sample spoken natural language commands and sample spoken natural language responses.