Example aspects of the present disclosure relate to an example computer-implemented method for predicting the intent of actors within an environment. The example method includes obtaining state data associated with a plurality of actors within the environment and map data indicating a plurality of lanes of the environment. The method include determining a plurality of potential goals each actor based on the state data and the map data. The method includes processing the state data, the map data, and the plurality of potential goals with a machine-learned forecasting model to determine (i) a forecasted goal for a respective actor of the plurality of actors, (ii) a forecasted interaction between the respective actor and a different actor of the plurality of actors based on the forecasted goal, and (iii) a continuous trajectory for the respective actor based on the forecasted goal.

Techniques for analysis of autonomous vehicle operations are described. As an example, a method of autonomous vehicle operation includes storing sensor data from one or more sensors located on the autonomous vehicle into a storage medium, performing, based on at least some of the sensor data, a simulated execution of one or more programs associated with the operations of the autonomous vehicle, generating, based on the simulated execution of the one or more programs and as part of a simulation, one or more control signal values that control a simulated driving behavior of a simulated vehicle, and providing a visual feedback of the simulated driving behavior of the simulated vehicle on a simulated road.

A method, apparatus and computer program product are provided for generating a transition variability index related to autonomous driving. In this regard, a first transition variability index is calculated. The first transition variability index is indicative of a first degree of variability in relation to transition of vehicles from respective autonomous levels while traveling proximate a first spatial reference point. Furthermore, a second transition variability index is generated. The second transition variability index is indicative of a second degree of variability in relation to transition of vehicles from respective autonomous levels while traveling along proximate a second spatial reference point. Updating of transition data associated with one of the first and second spatial reference points relative to another one of the first and second spatial reference points is then prioritized based on a comparison between the first transition variability index and the second transition variability index.

A system includes an autonomous vehicle and an oversight server. The oversight server receives status data from the autonomous vehicle. The oversight server determines that a service is needed to be provided to the autonomous vehicle based on the status data. The oversight server determines an updated routing plan for the autonomous vehicle so that the service is provided to the autonomous vehicle. The oversight server communicates instructions that implement the updated routing plan to the autonomous vehicle.

A system includes an autonomous vehicle and an oversight server. The oversight server obtain sensor data from the autonomous vehicle. The sensor data may include a location of the autonomous vehicle. The oversight server determines that one or more criteria apply to the autonomous vehicle based on the sensor data. The one or more criteria includes a geofence area, a particular time window, and a credential associated with a third party. The oversight server grants remote access to the autonomous vehicle in response to determining that the one or more criteria apply to the autonomous vehicle.

Proposed is a method of controlling an autonomous driving system. Root learning data is generated by performing learning for raw data. A plurality of first layer learning data is generated by performing learning, to which driving environment variables of an autonomous vehicle are applied, for the root learning data. The root learning data is updated from the plurality of first layer learning data depending on whether or not an integration condition of the plurality of first layer learning data is met.

A method of calibrating a driving force of a vehicle is provided. A status change of one or more components of the vehicle may be detected by a sensor. One or more models of the one or more components of the vehicle having the status change may be determined by the processing circuitry. The driving force based on the determined one or more models may be calculated by the processing circuitry. The driving force of the vehicle to reach a threshold value may be calibrated.

A system for determining an energy requirement of a vehicle for a journey. The system may comprise a predictor mechanism to predict, using an energy prediction algorithm, a vehicle energy requirement for the journey. The system comprises an updater mechanism configured to refine the energy prediction algorithm for the vehicle by determining for each of a number of historical journeys undertaken by the vehicle, an error between an actual vehicle energy usage for the historical journey and a predicted energy usage derived using the energy prediction algorithm for the historical journey. An aggregate error is calculated from the errors of the number of historical journeys. The updater is arranged to adjust the energy prediction algorithm to reduce the aggregate error.

An electronic control device includes: an acquisition unit that acquires state information indicating at least one of a state of a movable body and a state of an external environment in which the movable body is moving, and a control instruction indicating at least one of a steering control instruction for steering the movable body and an acceleration control instruction for adjusting acceleration of the movable body; and a determining unit that determines whether the control instruction is a false control instruction based on the at least one state indicated by the state information acquired and control indicated by the control instruction acquired.

Disclosed are probabilistic prediction for a motion of a lane-based surrounding vehicle and a longitudinal control method and apparatus using the same. The method includes obtaining surrounding vehicle information using a sensor, predicting a target lane of the surrounding vehicle based on the obtained surrounding vehicle information, performing future driving trajectory prediction for each target lane based on the surrounding vehicle information, and computing a probability of a collision likelihood based on a target lane and trajectory predictions of the surrounding vehicle in which future uncertainty has been taken into consideration and performing longitudinal control for collision avoidance.