Task impact zone and 4-dimensional safety envelope for robots

A non-transitory computer readable medium, including instructions which, if executed, cause a receiver to:

• receive a selected task from a plurality of possible tasks, wherein each possible task of the plurality of possible tasks is associated with a safety attribute of the possible task;
• and
• receive a perception prediction for an environment of an object, wherein the perception prediction comprises a predicted value of sensor data with respect to the object in the environment at the prediction time, wherein the predicted value of the sensor data is based on the safety envelope and comprises environmental information associated with the object at an expected position at a prediction time,
• wherein the instructions are further configured to cause a processor to:
• generate an instruction to move a robot according to a safe movement instruction based on whether a perception check exceeds a predetermined threshold, wherein the perception check is based on a difference between the perception prediction and sensor information indicative of the environment of the object at the prediction time, wherein the instructions further cause the processor to determine the prediction time based on a subinterval of an expected latency to move the robot according to the safe movement instruction;
• and
• control the robot to move according to the safe movement instruction.

An apparatus comprising:

• a means for receiving a safety envelope for an object, wherein the safety envelope comprises a reachable set of locations that the object may reach at an expected position of the object at a prediction time,
• a means for receiving a perception prediction for an environment of the object, wherein the perception prediction comprises a predicted value of sensor data with respect to the object in the environment at the prediction time, wherein the predicted value of the sensor data is based on the safety envelope and comprises environmental information associated with the object at the expected position at the prediction time, and
• a means for generating an instruction to move a robot according to a safe movement instruction based whether a perception check exceeds a predetermined threshold, wherein the perception check is based on a difference between the perception prediction and sensor information indicative of the environment of the object at the prediction time;
• a means for determining the prediction time based on a subinterval of an expected latency to move the robot according to the safe movement instruction;
• and
• a means for controlling the robot to move according to the safe movement instruction.