Mitigating the reality gap through optimization of one or more simulated hardware parameters for simulated hardware components of a simulated robot. Implementations generate and store real navigation data instances that are each based on a corresponding episode of locomotion of a real robot. A real navigation data instance can include a sequence of velocity control instances generated to control a real robot during a real episode of locomotion of the real robot, and one or more ground truth values, where each of the ground truth values is a measured value of a corresponding property of the real robot (e.g., pose). The velocity control instances can be applied to a simulated robot, and one or more losses can be generated based on comparing the ground truth value(s) to corresponding simulated value(s) generated from applying the velocity control instances to the simulated robot. The simulated hardware parameters and environmental parameters can be optimized based on the loss(es).

A computer-implemented method is provided for autonomously controlling a vehicle to perform a vehicle operation. The method includes steps of applying a passive actor-critic reinforcement learning method to passively-collected data relating to the vehicle operation, to learn a control policy configured for controlling the vehicle so as to perform the vehicle operation with a minimum expected cumulative cost; and controlling the vehicle in accordance with the control policy to perform the vehicle operation.

A computer-implemented method of adaptively controlling an autonomous operation of a vehicle is provided. The method includes steps of (a) in a critic network in a computing system configured to autonomously control the vehicle, determining, using samples of passively collected data and a state cost, an estimated average cost, and an approximated cost-to-go function that produces a minimum value for a cost-to-go of the vehicle when applied by an actor network; and (b) in an actor network in the computing system and operatively coupled to the critic network, determining a control input to apply to the vehicle that produces the minimum value for the cost-to-go, wherein the actor network is configured to determine the control input by estimating a noise level using the average cost, a cost-to-go determined from the approximated cost-to-go function, a control dynamics for a current state of the vehicle, and the passively collected data.

In one embodiment, motion planning and control data is received, where the motion planning and control data indicates that an autonomous vehicle is to move from a first point to a second point of a path within a predetermined route. In response to the motion planning and control data, the path from the first point to the second point is segmented into multiple path segments. For each of the path segments, one of predetermined driving scenes is identified that matches motion characteristics of the corresponding path segment. The motion planning and control data associated with the path segments is modified based on predetermined motion settings of the path segments. The autonomous vehicle is driven through the path segments of the path based on the modified motion planning and control data.

Systems and methods for determining object prioritization and predicting future object locations for an autonomous vehicle are provided. A method can include obtaining, by a computing system comprising one or more processors, state data descriptive of at least a current or past state of a plurality of objects that are perceived by an autonomous vehicle. The method can further include determining, by the computing system, a priority classification for each object in the plurality of objects based at least in part on the respective state data for each object. The method can further include determining, by the computing system, an order at which the computing system determines a predicted future state for each object based at least in part on the priority classification for each object and determining, by the computing system, the predicted future state for each object based at least in part on the determined order.

Systems and methods for curiosity development in an agent located in an uncertain environment are provided. In one embodiment, the system includes a goal state module, a curiosity module, and a planning module. The goal module is configured to calculate a goal state of a goal associated with the environment. The curiosity module is configured to determine an uncertainty value for the environment and calculate a curiosity reward based on the uncertainty value. The planning module is configured to update a motion plan based on the goal state and the curiosity reward.

Embodiments herein can determine an optimal route for an autonomous electric vehicle. The system may score viable routes between the start and end locations of a trip using a numeric or other scale that denotes how viable the route is for autonomy. The score is adjusted using a variety of factors where a learning process leverages both offline and online data. The scored routes are not based simply on the shortest distance between the start and end points but determine the best route based on the driving context for the vehicle and the user.

A system and method for real world autonomous vehicle trajectory simulation may include: receiving training data from a data collection system; obtaining ground truth data corresponding to the training data; performing a training phase to train a plurality of trajectory prediction models; and performing a simulation or operational phase to generate a vicinal scenario for each simulated vehicle in an iteration of a simulation. Vicinal scenarios may correspond to different locations, traffic patterns, or environmental conditions being simulated. Vehicle intention data corresponding to a data representation of various types of simulated vehicle or driver intentions.

Systems and methods for route synchronization between two or more robots to allow for a single training run of a route to effectively train multiple robots to follow the route.

A robot device includes: a sensor configured to generate sensing data related to an action of the robot device; a communication interface configured to communicate with a server; a memory storing instructions; and a processor configured to execute the instructions to: based on the action of the robot device changing, store action data in the memory, the action data including instruction data corresponding to the action, the sensing data related to the action, and map data related to the action, transmit, to the server via the communication interface, the action data stored in the memory, receive, from the server via the communication interface, threshold data corresponding to the action, and based on identifying that the sensing data is outside of a threshold range based on the threshold data received from the server, generate an event.