Abstract: A system and method for using human driving patterns to manage speed control for autonomous vehicles are disclosed. A particular embodiment includes: generating data corresponding to desired human driving behaviors; training a human driving model module using a reinforcement learning process and the desired human driving behaviors; receiving a proposed vehicle speed control command; determining if the proposed vehicle speed control command conforms to the desired human driving behaviors by use of the human driving model module; and validating or modifying the proposed vehicle speed control command based on the determination.

Abstract: A data-driven prediction-based system and method for trajectory planning of autonomous vehicles are disclosed. A particular embodiment includes: generating a first suggested trajectory for an autonomous vehicle; generating predicted resulting trajectories of proximate agents using a prediction module; scoring the first suggested trajectory based on the predicted resulting trajectories of the proximate agents; generating a second suggested trajectory for the autonomous vehicle and generating corresponding predicted resulting trajectories of proximate agents, if the score of the first suggested trajectory is below a minimum acceptable threshold; and outputting a suggested trajectory for the autonomous vehicle wherein the score corresponding to the suggested trajectory is at or above the minimum acceptable threshold.

Abstract: Disclosed are devices, systems and methods for incorporating a smoothness constraint for camera pose estimation. One method for robust camera pose estimation includes determining a first bounding box based on a previous frame, determining a second bounding box based on a current frame that is temporally subsequent to the previous frame, estimating the camera pose by minimizing a weighted sum of a camera pose function and a constraint function, where the camera pose function tracks a position and an orientation of the camera in time, and where the constraint function is based on coordinates of the first bounding box and coordinates of the second bounding box, and using the camera pose for navigating the vehicle. The method may further include generating an initial estimate of the camera pose is based on a Global Positioning System (GPS) sensor or an Inertial Measurement Unit (IMU).

Abstract: A method of localization for a non-transitory computer readable storage medium storing one or more programs is disclosed. The one or more programs comprise instructions, which when executed by a computing device, cause the computing device to perform by one or more autonomous vehicle driving modules execution of processing of images from a camera and data from a LiDAR using the following steps comprising: computing, in response to features from a 3D submap and features from a global map, matching score between corresponding features of a same class between the 3D submap and the global map; selecting, for each feature in the 3D submap, a corresponding feature with the highest matching score from the global map; determining a feature correspondence to be invalid if a distance between corresponding features is larger than a threshold; and removing the invalid feature correspondence.