Autonomous unknown object pick and place
A set of one or more potentially graspable features for one or more objects present in a workspace area are determined based on visual data received from a plurality of cameras. For each of at least a subset of the one or more potentially graspable features one or more corresponding grasp strategies are determined to grasp the feature with a robotic arm and end effector. A score associated with a probability of a successful grasp of a corresponding feature is determined with respect to each of a least a subset of said grasp strategies. A first feature of the one or more potentially graspable features is selected to be grasped using a selected grasp strategy based at least in part on a corresponding score associated with the selected grasp strategy with respect to the first feature. The robotic arm and the end effector are controlled to attempt to grasp the first feature using the selected grasp strategy.
1. A method, comprising:
determining, based on visual data received from a plurality of cameras, a set of one or more potentially graspable features for one or more objects present in a workspace area;
determining for each of at least a subset of the one or more potentially graspable features one or more corresponding grasp strategies to grasp a feature with a robotic arm and end effector;
determining with respect to each of a least a subset of said one or more corresponding grasp strategies a score associated with a probability of a successful grasp of a corresponding feature;
selecting to grasp a first feature of the one or more potentially graspable features using a selected grasp strategy based at least in part on a corresponding score associated with the selected grasp strategy with respect to the first feature; and
controlling the robotic arm and end effector to attempt to grasp the first feature using the selected grasp strategy, wherein grasping the first feature using the selected grasp strategy comprises:
determining whether a grasp of the first feature is successful, wherein in response to a determination that the grasp of the first feature is determined not to be successful, iteratively re-attempting to grasp the first feature using the selected grasp strategy or implementing a different grasp strategy to grasp the first feature until a threshold number of attempts to grasp the first feature have been attempted; and
in response to the threshold number of attempts having been attempted, selecting a second feature of the one or more potentially graspable features to grasp.
2. The method of claim 1 , wherein the visual data received from the plurality of cameras includes point cloud data.
3. The method of claim 1 , further comprising determining boundary information associated with the one or more objects based on the visual data received from the plurality of cameras.
4. The method of claim 3 , wherein the selected grasp strategy is selected based in part on the determined boundary information associated with the one or more objects.
5. The method of claim 1 , further comprising segmenting one of the one or more objects into a plurality of shapes.
6. The method of claim 1 , wherein the first feature has a highest score associated with the probability of the successful grasp of the corresponding feature.
7. The method of claim 1 , wherein at least one of the plurality of cameras is dynamically moving.
8. The method of claim 1 , wherein at least one of the plurality of cameras is at a fixed location.
9. The method of claim 1 , wherein in response to a determination that the grasp of the second feature is determined to be successful, an object associated with the second feature is moved to a drop off area.
10. The method of claim 1 , wherein the visual data received from the plurality of cameras is used to determine negative space information associated with the one or more objects.
11. The method of claim 1 , wherein the one or more potentially graspable features includes a handle, a protrusion, or a void.
12. The method of claim 1 , further comprising:
detecting a human in the workspace area; and
selecting a third feature associated with a second object based on whether the human is located in a same zone as the first feature associated with a first object.
13. The method of claim 1 , further comprising:
detecting a human in the workspace area; and
stopping operation of the robotic arm in the event the human is detected in a same zone as the first feature associated with an object.
14. The method of claim 1 , further comprising moving an object associated with the first feature to a drop off area.
15. The method of claim 14 , further comprising determining whether the object has been dropped.
16. The method of claim 1 , further comprising placing an object associated with the first feature in a drop off area.
17. The method of claim 1 , further comprising recalibrating a robotic system associated with the robotic arm and the end effector based on whether a miscalibration condition has occurred.
18. The method of claim 1 , further comprising updating an operation of a robotic system associated with the robotic arm and the end effector based on whether a new object is detected in the workspace area.
19. A non-transitory computer storage readable medium and comprising instructions for:
determining, based on visual data received from a plurality of cameras, a set of one or more potentially graspable features for one or more objects present in a workspace area;
determining for each of at least a subset of the one or more potentially graspable features one or more corresponding grasp strategies to grasp a feature with a robotic arm and end effector;
determining with respect to each of a least a subset of said one or more corresponding grasp strategies a score associated with a probability of a successful grasp of a corresponding feature;
selecting to grasp a first feature of the one or more potentially graspable features using a selected grasp strategy based at least in part on a corresponding score associated with the selected grasp strategy with respect to the first feature; and
controlling the robotic arm and the end effector to attempt to grasp the first feature using the selected grasp strategy, wherein grasping the first feature using the selected grasp strategy comprises:
determining whether a grasp of the first feature is successful, wherein in response to a determination that the grasp of the first feature is determined not to be successful, iteratively re-attempting to grasp the first feature using the selected grasp strategy or implementing a different grasp strategy to grasp the first feature until a threshold number of attempts to grasp the first feature have been attempted; and
in response to the threshold number of attempts having been attempted, selecting a second feature of the one or more potentially graspable features to grasp.
20. A system, comprising:
a communication interface; and
a processor coupled to the communication interface and configured to:
determine, based on visual data received from a plurality of cameras, a set of one or more potentially graspable features for one or more objects present in a workspace area;
determine for each of at least a subset of the one or more potentially graspable features one or more corresponding grasp strategies to grasp a feature with a robotic arm and end effector;
determine with respect to each of a least a subset of said one or more corresponding grasp strategies a score associated with a probability of a successful grasp of a corresponding feature;
select to grasp a first feature of the one or more potentially graspable features using a selected grasp strategy based at least in part on a corresponding score associated with the selected grasp strategy with respect to the first feature; and
control the robotic arm and end effector to attempt to grasp the first feature using the selected grasp strategy, wherein grasping the first feature using the selected grasp strategy comprises:
determining whether a grasp of the first feature is successful, wherein in response to a determination that the grasp of the first feature is determined not to be successful, iteratively re-attempting to grasp the first feature using the selected grasp strategy or implementing a different grasp strategy to grasp the first feature until a threshold number of attempts to grasp the first feature have been attempted; and
in response to the threshold number of attempts having been attempted, selecting a second feature of the one or more potentially graspable features to grasp.