Vision System to Recognize Pedestrian Intention
University of Michigan researchers are interpreting body language to determine a pedestrian’s intention. The system processes lidar and stereo camera images to estimate not just a person’s trajectory, but their pose and gait. Pose can indicate whether a person is looking towards or away from the car, using a cane, or stooped over a phone. Gait indicates not just speed but also intention. The work was supported by a grant from Ford Motor Company.
Related Posts
Robotic Trucks Using Peripheral Vision. See For Yourself
Kodiak Robotics Inc is adding Hesai Technology Co’s LIDAR to its autonomous trucks for peripheral vision. The trucks will keep their one…
Things are Looking Good for Unicorn Aeva
Aeva Inc. makes a 3D LIDAR that detects the velocity of distant objects, which is especially useful for trucks because they need a longer…
Waymo lands $2.25B and releases self-driving electric 5Gen Jaguar
Waymo is launching. A fresh $2.25 billion external investment round validates its plan and progress and will help to expand its offerings,…