Deterministic robot path planning method for obstacle avoidance

1. A method, implemented on a machine having at least one processor, storage, and a communication platform capable of connecting to a network for path planning, the method comprising:

tracking, via one or more sensors, a target;

obtaining information of a desired pose of an end-effector with respect to the target;

obtaining a current pose of the end-effector;

obtaining a minimum distance permitted between an arm including the end-effector and each of at least one obstacle identified between the current pose of the end-effector and the target;

retrieving, prior to computing a cost function, a weighting factor, the weighting factor defining a relationship between a joint angle cost and an obstacle-distance cost, wherein the weighting factor is iteratively learned over a predetermined number of iterations;

for each iteration of the predetermined number of iterations:

generating a random desired position of the end-effector;

selecting an initial value of the weighting factor;

minimizing the cost function based on the initial value; and

determining a path based on the minimizing;

computing a cost based on the cost function in accordance with a weighted smallest distance between the arm including the end-effector and the at least one obstacle, wherein the smallest distance is weighted by the weighting factor; and

computing a trajectory from the current pose to the desired pose by minimizing the cost function.

2. The method of claim 1 , further comprising:

obtaining, based on the path, an actual minimum distance of the arm including the end-effector with respect to the at least one obstacle;

computing an error corresponding to a difference between the actual distance and the minimum distance permitted; and

updating the weighting factor based on the error.

3. The method of claim 2 , wherein the weighting factor is updated based on the error and a positive scale parameter.

4. The method of claim 2 , further comprising: determining, whether the weighting factor satisfies a criterion;

in response to the weighting factor satisfying the criterion, recording the weighting factor corresponding to the iteration; and

in response to weighting factor not satisfying the criterion, updating the weighting factor.

5. The method of claim 4 , further comprising:

in response to completing the predetermined number of iterations, computing a weighted sum of the recorded weighing factors of each iteration.

6. The method of claim 1 , wherein the minimum distance permitted between the arm including the end-effector and each of at least one obstacle is determined based on a type of the at least one obstacle.

7. The method of claim 1 , wherein the step of obtaining information of a desired pose of an end-effector with respect to the target, further comprises:

obtaining the desired pose of the end-effector in a first coordinate system; and

transforming the desired pose of the end-effector from the first coordinate system to a second coordinate system.

8. The method of claim 1 , wherein the weighting factor is greater than zero.

9. A system for path planning, the system comprising: at least one processor configured to

track, via one or more sensors, a target;

obtain information of a desired pose of an end-effector with respect to the target; obtain a current pose of the end-effector;

obtain a minimum distance permitted between an arm including the end-effector and each of at least one obstacle identified between the current pose of the end-effector and the target;

retrieve, prior to computing a cost function, a weighting factor, the weighting factor defining a relationship between a joint angle cost and an obstacle-distance cost, wherein the weighting factor is iteratively learned over a predetermined number of iterations;

for each iteration of the predetermined number of iterations:

generate a random desired position of the end-effector;

select an initial value of the weighting factor;

minimize the cost function based on the initial value; and

determine a path based on the minimizing;

compute a cost based on a cost function in accordance with a weighted smallest distance between the arm including the end-effector and the at least one obstacle, wherein the smallest distance is weighted by the weighting factor; and

compute a trajectory from the current pose to the desired pose by minimizing the cost function.

10. The system of claim 9 , wherein the at least one processor is further configured to:

obtain, based on the path, an actual minimum distance of the arm including end-effector with respect to the at least one obstacle;

compute an error corresponding to a difference between the actual distance and the minimum distance permitted; and

update the weighting factor based on the error.

11. The system of claim 10 , wherein the weighting factor is updated based on the error and a positive scale parameter.

12. The system of claim 10 , wherein the at least one processor is further configured to:

determine, whether the weighting factor satisfies a criterion;

in response to the weighting factor satisfying the criterion, record the weighting factor corresponding to the iteration; and

in response to weighting factor not satisfying the criterion, update the weighting factor.

13. The system of claim 12 , wherein the at least one processor is further configured to:

in response to completing the predetermined number of iterations, compute a weighted sum of the recorded weighing factors of each iteration.

14. The system of claim 9 , wherein the minimum distance permitted between the arm including the end-effector and each of at least one obstacle is determined based on a type of the at least one obstacle.

15. The system of claim 9 , wherein the at least one processor is further configured to:

obtain the desired pose of the end-effector in a first coordinate system; and transform the desired pose of the end-effector from the first coordinate system to a second coordinate system.

16. The system of claim 9 , wherein the weighting factor is greater than zero.