| CPC B25J 9/1666 (2013.01) [B25J 9/163 (2013.01); B25J 9/1671 (2013.01); G05B 2219/40371 (2013.01); G05B 2219/40476 (2013.01)] | 20 Claims |

|
1. A method, comprising:
obtaining, via at least one sensor, a current pose of a multi-joint robotic arm;
calculating, via at least one processor, a minimum distance permitted between the multi-joint robotic arm and at least one obstacle identified between the current pose and a target;
calculating, via the at least one processor, a weighting factor, the weighting factor defining a relationship between a joint angle cost of joints within the multi-joint robotic arm and an obstacle-distance cost,
wherein the weighting factor is iteratively learned over a predetermined number of iterations by minimizing a cost function over a plurality of iterations using, for each iteration, a random desired position of an end-effector of the multi-joint robotic arm;
computing, via the at least one processor, a trajectory from the current pose to the target by minimizing the cost function using the weighting factor; and
initiating, via the at least one processor, movement of the multi-joint robotic arm along the trajectory.
|