Abstract: Systems and methods for trajectory prediction are provided. A method can include obtaining LIDAR data, radar data, and map data; inputting the LIDAR data, the radar data, and the map data into a network model; transforming, by the network model, the radar data into a coordinate frame associated with a most recent radar sweep in the radar data; generating, by the network model, one or more features for each of the LIDAR data, the transformed radar data, and the map data; combining, by the network model, the one or more generated features to generate fused feature data; generating, by the network model, prediction data based at least in part on the fused feature data; and receiving, as an output of the network model, the prediction data. The prediction data can include a respective predicted trajectory for a future time period for one or more detected objects.

Abstract: Systems and methods for trajectory prediction are provided. A method can include obtaining LIDAR data, radar data, and map data; inputting the LIDAR data, the radar data, and the map data into a network model; transforming, by the network model, the radar data into a coordinate frame associated with a most recent radar sweep in the radar data; generating, by the network model, one or more features for each of the LIDAR data, the transformed radar data, and the map data; combining, by the network model, the one or more generated features to generate fused feature data; generating, by the network model, prediction data based at least in part on the fused feature data; and receiving, as an output of the network model, the prediction data. The prediction data can include a respective predicted trajectory for a future time period for one or more detected objects.

Abstract: The present disclosure provides systems and methods for controlling a sensor system. More particularly, a sensor control system can access respective first data and second data descriptive of one or more monitored parameters associated with a first sensor of an autonomous vehicle. Based on the first data and the second data, the sensor control system can determine that a change in the one or more monitored parameters between the first sensor and the one or more second sensors has exceeded a predetermined threshold level. In response, the sensor control system can implement a control action relative to at least the first sensor (e.g., initiating cleaning of the first sensor, adjusting alignment of the first sensor, determining a compensation factor for the first data received from the first sensor, or communicating a signal request for service of the first sensor).

Abstract: The present disclosure provides systems and methods for controlling a sensor system. More particularly, a sensor control system can access respective first data and second data descriptive of one or more monitored parameters associated with a first sensor of an autonomous vehicle. Based on the first data and the second data, the sensor control system can determine that a change in the one or more monitored parameters between the first sensor and the one or more second sensors has exceeded a predetermined threshold level. In response, the sensor control system can implement a control action relative to at least the first sensor (e.g., initiating cleaning of the first sensor, adjusting alignment of the first sensor, determining a compensation factor for the first data received from the first sensor, or communicating a signal request for service of the first sensor).

Abstract: Structural steel profiles such as channels, having a material thickness greater than 2 mm, are roll-formed to a preform profile with corners partial bent, in-line galvanized, and then further roll-formed to final shape. The preform profile has upwardly facing convex surfaces allowing rapid shedding of excess galvanising material. By preforming corners before galvanising, surface elongation in the galvanising layer is minimized and cracking eliminated. This is enhances by constant length bending of corners over preform and final roll-forming operations.