Trajectory planning with droppable objects

Patent metadata

Field	Value
Publication number	US-9821458-B1
Application number	US-201615150756-A
Country	US
Kind code	B1
Filing date	May 10, 2016
Priority date	May 10, 2016
Publication date	Nov 21, 2017
Grant date	Nov 21, 2017

Abstract

Example implementations may relate to methods and systems for determining a safe trajectory for movement of an object by a robotic system. According to these various implementations, the robotic system may determine at least first and second candidate trajectories for moving the object. For at least a first point along the first candidate trajectory, the robotic system may determine a predicted cost of dropping the object at the first point along the first candidate trajectory. And for at least a second point along the second candidate trajectory, the robotic system may determine a predicted cost of dropping the object at the second point along the second candidate trajectory. Then, based on these various determined predicted costs, the robotic system may select between the first and second candidates trajectories and may then move the object along the selected trajectory.

First claim

I claim:

1. A method comprising:
determining, by a robotic system, at least first and second candidate trajectories for moving an object in an environment from a first location to a second location;
for at least a first point along the first candidate trajectory, the robotic system determining a predicted cost of dropping the object at the first point along the first candidate trajectory;
for at least a second point along the second candidate trajectory, the robotic system determining a predicted cost of dropping the object at the second point along the second candidate trajectory;
based at least on the determined predicted cost for the first point along the first candidate trajectory and on the determined predicted cost for the second point along the second candidate trajectory, the robotic system selecting between the first and second candidate trajectories; and
the robotic system moving the object from the first location to the second location along the selected trajectory.

2. The method of claim 1 , further comprising:
for at least the first point along the first candidate trajectory, the robotic system determining a probability of the robotic system dropping the object at the first point along the first candidate trajectory; and
for at least the second point along the second candidate trajectory, the robotic system determining a probability of the robotic system dropping the object at the second point along the second candidate trajectory,
wherein selecting between the first and second candidates trajectories is further based on the determined probability for the first point along the first candidate trajectory and on the determined probability for the second point along the second candidate trajectory.

3. The method of claim 2 , wherein determining the probability of the robotic system dropping the object at the first point along the first candidate trajectory comprises:
determining (i) a velocity of the object at the first point along the first candidate trajectory, (ii) an acceleration of the object at the first point along the first candidate trajectory, and (iii) a grasp quality level representative of quality with which the robotic system grasps the object at the first point along the first candidate trajectory; and
based at least on (i) the determined velocity, (ii) the determined acceleration, and (iii) the determined grasp quality level, determining the probability of the robotic system dropping the object at the first point along the first candidate trajectory.

4. The method of claim 1 , further comprising:
the robotic system determining a predicted cost of dropping the object at a third point that is along the first candidate trajectory; and
the robotic system determining a predicted cost of dropping the object at a fourth point that is along the second candidate trajectory,
wherein selecting between the first and second candidate trajectories is further based on the determined predicted cost for the third point along the first candidate trajectory and on the determined predicted cost for the fourth point along the second candidate trajectory.

5. The method of claim 4 , further comprising:
the robotic system determining at least (i) a probability of the robotic system dropping the object at the first point along the first candidate trajectory and (ii) a probability of the robotic system dropping the object at the third point along the first candidate trajectory; and
the robotic system determining at least (i) a probability of the robotic system dropping the object at the second point along the second candidate trajectory and (ii) a probability of the robotic system dropping the object at the fourth point along the second candidate trajectory,
wherein selecting between the first and second candidates trajectories is further based on the determined probabilities for the first and third points along the first candidate trajectory and on the determined probability for the second and fourth points along the second candidate trajectory.

6. The method of claim 5 , wherein selecting between the first and second candidates trajectories based on the determined probabilities and predicted costs for the first and third points along the first candidate trajectory and on the determined probabilities and predicted costs for the second and fourth points along the second candidate trajectory comprises:
based on the predicted costs and probabilities respectively determined for the first and third points along the first candidate trajectory, determining a first score associated with moving the object from the first location to the second location along the first candidate trajectory, wherein determining the first score comprises, for each given point of the first and third points along the first candidate trajectory, weighting the determined predicted cost at the given point by the determined probability at the given point;
based on the predicted costs and probabilities respectively determined for the second and fourth points along the second candidate trajectory, determining a second score associated with moving the object from the first location to the second location along the second candidate trajectory, wherein determining the second score comprises, for each given point of the second and fourth points along the second candidate trajectory, weighting the determined predicted cost at the given point by the determined probability at the given point;
making a comparison between the first and second scores; and
based on the comparison, selecting between the first and second candidates trajectories.

7. The method of claim 1 , further comprising:
for each given point of a plurality of points along the first candidate trajectory, the robotic system determining a predicted cost of dropping the object at the given point along the first candidate trajectory; and
for each given point of a plurality of points along the second candidate trajectory, the robotic system determining a predicted cost of dropping the object at the given point along the second candidate trajectory,
wherein the first point is one of the plurality of points along the first candidate trajectory, wherein the second point is one of the plurality of points along the second candidate trajectory, and wherein selecting between the first and second candidate trajectories is further based on the determined predicted costs for the plurality of points along the first candidate trajectory and on the determined predicted costs for the plurality of points along the second candidate trajectory.

8. The method of claim 7 , further comprising:
determining, by the robotic system, the plurality of points along the first candidate trajectory by selecting one or more points distributed along the first candidate trajectory at a particular spatial interval.

9. The method of claim 7 , further comprising:
determining, by the robotic system, the plurality of points along the first candidate trajectory by determining along the first candidate trajectory one or more inflection points each defining a point of transition between a convex segment of the first candidate trajectory and a concave segment of the first candidate trajectory.

10. The method of claim 7 , wherein selecting between the first and second candidates trajectories comprises:
based on the predicted costs respectively determined for the plurality of points along the first candidate trajectory, determining a first overall predicted cost of moving the object from the first location to the second location along the first candidate trajectory;
based on the predicted costs respectively determined for the plurality of points along the second candidate trajectory, determining a second overall pre

Assignees

• X Dev Llc

Inventors

• Watts Kevin William

Classifications

• B25J9/1664 Primary

  characterised by motion, path, trajectory planning · CPC title

• G05B2219/39289

  Adaptive ann controller · CPC title

• B25J9/163 Primary

  learning, adaptive, model based, rule based expert control · CPC title

• B25J9/1612

  characterised by the hand, wrist, grip control · CPC title

• G05B2219/39266

  Algorithm for control · CPC title