Abstract: A robotic system is disclosed that uses autonomous tunnel navigation. The system includes a plurality of sensors (e.g., ranging, odometry) to measure a distance from the robotic system to a plurality of walls. Memory stores instructions and a processor is coupled to the memory and the plurality of sensors to execute the instructions. The instructions cause the robotic system to detect movement of the robotic system through a surrounding environment based on sensor measurements, determine if the robotic system is in a tunnel based on the sensor measurements, and navigate with the odometry-based sensor when the robotic system is determined to be in the tunnel or the ranging sensor when the robotic system is determined to be not in the tunnel.

Abstract: A system and method of teaching a neural network through reinforcement learning methodology. The system includes a machine-readable medium having one or more processors that perform a motion task to produce a first result corresponding to navigating a device during a first episode and performing an interaction task during that same episode. After completion of the first episode a processor calculates a Q value change based on the first task result and the second task result. The processor then modifies parameters based on the Q value change such that during subsequent episode iterations the motion task and interactive task are improved and a smooth and continuous transition occurs between these two tasks.

Abstract: A system and method of teaching a neural network through reinforcement learning methodology. The system includes a machine-readable medium having one or more processors that perform a motion task to produce a first result corresponding to navigating a device during a first episode and performing an interaction task during that same episode. After completion of the first episode a processor calculates a Q value change based on the first task result and the second task result. The processor then modifies parameters based on the Q value change such that during subsequent episode iterations the motion task and interactive task are improved and a smooth and continuous transition occurs between these two tasks.

Abstract: A robotic system is disclosed that uses autonomous tunnel navigation. The system includes a plurality of sensors (e.g., ranging, odometry) to measure a distance from the robotic system to a plurality of walls. Memory stores instructions and a processor is coupled to the memory and the plurality of sensors to execute the instructions. The instructions cause the robotic system to detect movement of the robotic system through a surrounding environment based on sensor measurements, determine if the robotic system is in a tunnel based on the sensor measurements, and navigate with the odometry-based sensor when the robotic system is determined to be in the tunnel or the ranging sensor when the robotic system is determined to be not in the tunnel.

Abstract: A processing device includes a first processor module comprising a first core designed according to a first instruction set (ISA), and a second processor module comprising a second core designed according to a second ISA. The first and second processor modules are fabricated on a same die.