In various examples, live perception from sensors of a vehicle may be leveraged to generate potential paths for the vehicle to navigate an intersection in real-time or near real-time. For example, a deep neural network (DNN) may be trained to compute various outputssuch as heat maps corresponding to key points associated with the intersection, vector fields corresponding to directionality, heading, and offsets with respect to lanes, intensity maps corresponding to widths of lanes, and/or classifications corresponding to line segments of the intersection. The outputs may be decoded and/or otherwise post-processed to reconstruct an intersectionor key points corresponding theretoand to determine proposed or potential paths for navigating the vehicle through the intersection.

An event recognition system includes one or more processing circuits including one or more memory devices and one or more processors. The one or more memory devices are configured to store instructions thereon that, when executed by the one or more processors, cause the one or more processors to: execute an algorithm that receives image data as an input and recognizes a first equipment object and a second equipment object in the image data; recognize an event involving the first equipment object and the second equipment object based upon the image data containing the recognized first equipment object and the recognized second equipment object; and execute an event procedure based upon the event where the event procedure includes controlling the first equipment object.

The present disclosure provides a multi-vehicle omnidirectional aircraft maneuvering system comprising a plurality of tow vehicles, each tow vehicle comprising a turntable lifting unit (TLU) configured to capture and secure a portion of an aircraft's landing gear, a control unit configured to communicate with and coordinate the movements of the plurality of tow vehicles, and wherein each TLU comprises an automated turntable, a gate configured to open and close to receive landing gear, and a moving floor configured to support the landing gear. The system enables precise positioning and omnidirectional movement of aircraft through coordinated operation of multiple tow vehicles that simultaneously engage with different landing gear components. Each tow vehicle includes sensors for detecting landing gear position and environmental conditions, while the control unit establishes wireless communication to synchronize lifting operations and coordinate simultaneous movement patterns. The turntable lifting units provide rotational capability while maintaining secure engagement with the aircraft's landing gear, allowing for complex maneuvering operations in confined spaces such as aircraft hangars and maintenance facilities.

A system for autonomous aircraft towing includes a tow vehicle with a turntable lifting unit for engaging an aircraft's nose landing gear, a sensor system, and an Offline Intelligence Advanced Driver Assistance System (OI-ADAS) integrated with the tow vehicle. The OI-ADAS includes a local processing unit that processes sensor data in volatile memory without persistent storage and a controller that analyzes visual cues to determine position and orientation, generates control commands, controls the turntable lifting unit, and maneuvers the tow vehicle. The OI-ADAS operates without preexisting knowledge of the environment, processing all data exclusively in volatile memory and discarding visual frames after processing. The system detects visual cues on ground surfaces for navigation without relying on pre-existing maps or GPS data. A collision avoidance module detects obstacles and generates avoidance maneuvers in autonomous mode while providing warnings and intervention in operator-controlled mode.