Terrain aware step planning system
A method for terrain and constraint planning a step plan includes receiving, at data processing hardware of a robot, image data of an environment about the robot from at least one image sensor. The robot includes a body and legs. The method also includes generating, by the data processing hardware, a body-obstacle map, a ground height map, and a step-obstacle map based on the image data and generating, by the data processing hardware, a body path for movement of the body of the robot while maneuvering in the environment based on the body-obstacle map. The method also includes generating, by the data processing hardware, a step path for the legs of the robot while maneuvering in the environment based on the body path, the body-obstacle map, the ground height map, and the step-obstacle map.
1. A computer-implemented method when executed by data processing hardware of a robot causes the data processing hardware to perform operations, the robot comprising a body and legs coupled to the body, the operations comprising:
obtaining a body-obstacle map identifying body obstacles present in an environment of the robot, each body obstacle representative of a body object in the environment that may collide with the body of the robot;
obtaining a step-obstacle map identifying step obstacles present in the environment, each step obstacle representative of a step object in the environment that may collide with the legs of the robot;
generating, using the body-obstacle map and without using the step-obstacle map, a body path defining a path for movement of the body of the robot from a body path start to a body path destination;
generating, using the body path, a step path defining step positions for the legs of the robot along the body path; and
determining, using the step-obstacle map, an adjusted step path, the adjusted step path avoiding collisions between the legs of the robot and the step obstacles encountered by the robot as the body of the robot travels along the body path.
2. The method of claim 1 , wherein generating the step path comprises determining, based on the step-obstacle map, an initial gait pattern having an initial gait timing.
3. The method of claim 2 , wherein determining the initial gait pattern comprises selecting the initial gait pattern from a plurality of initial gait patterns, each initial gait pattern of the plurality of initial gait patterns having a corresponding initial gait timing.
4. The method of claim 3 , wherein:
each respective initial gait pattern of the plurality of initial gait patterns is weighted based on a respective quality of the step positions for the legs of the robot along the step path using the respective initial gait pattern; and
selecting the initial gait pattern is based on the respective qualities of the step positions for the legs of the robot along the step path using the respective initial gait patterns.
5. The method of claim 1 , wherein determining the adjusted step path is based on one or more step constraints.
6. The method of claim 5 , wherein:
the one or more step constraints include:
one or more hard constraints that the adjusted step path cannot violate; and
one or more soft constraints, whereby each respective soft constraint of the one or more soft constraints is weighted based on a respective cost of the adjusted step path violating the respective soft constraint; and
determining the adjusted step path is based on the respective costs of the adjusted step path violating the respective soft constraints.
7. The method of claim 6 , wherein:
the adjusted step path violates at least one of the one or more soft constraints; and
the respective cost corresponding to each violated soft constraint is less than a threshold cost.
8. The method of claim 6 , wherein:
the adjusted step path violates at least one of the one or more soft constraints; and
a sum of the respective costs corresponding to each violated soft constraint is less than a threshold cost.
9. The method of claim 5 , wherein the one or more step constraints comprise at least one of:
a threshold range of a center of pressure offset for each leg in contact with a ground surface, the center of pressure offset indicating an acceptable amount of robot weight distribution for each leg at each step position;
whether the adjusted step path causes a leg to step into a no-step region of the step-obstacle map;
whether the adjusted step path causes the body of the robot to enter a no-body region of the body-obstacle map;
whether the adjusted step path causes a self-collision of the robot; or
a margin of space about any no-step region of the step-obstacle map.
10. The method of claim 1 , wherein the operations comprise determining, using the adjusted step path, an adjusted body path, the adjusted body path based on movement of the body of the robot as the legs of the robot travel along the adjusted step path.
11. A robot comprising:
a body;
legs coupled to the body and configured to maneuver the robot about an environment of the robot;
data processing hardware in communication with the legs; and
memory hardware in communication with the data processing hardware, the memory hardware storing instructions that when executed on the data processing hardware cause the data processing hardware to perform operations comprising:
obtaining a body-obstacle map identifying body obstacles present in the environment, each body obstacle representative of a body object in the environment that may collide with the body of the robot;
obtaining a step-obstacle map identifying step obstacles present in the environment, each step obstacle representative of a step object in the environment that may collide with the legs of the robot;
generating, using the body-obstacle map and without using the step-obstacle map, a body path defining a path for movement of the body of the robot from a body path start to a body path destination;
generating, using the body path, a step path defining step positions for the legs of the robot along the body path; and
determining, using the step-obstacle map, an adjusted step path, the adjusted step path avoiding collisions between the legs of the robot and the step obstacles encountered by the robot as the body of the robot travels along the body path.
12. The robot of claim 11 , wherein generating the step path comprises determining, based on the step-obstacle map, an initial gait pattern having an initial gait timing.
13. The robot of claim 12 , wherein determining the initial gait pattern comprises selecting the initial gait pattern from a plurality of initial gait patterns, each initial gait pattern of the plurality of initial gait patterns having a corresponding initial gait timing.
14. The robot of claim 13 , wherein:
each respective initial gait pattern of the plurality of initial gait patterns is weighted based on a respective quality of the step positions for the legs of the robot along the step path using the respective initial gait pattern; and
selecting the initial gait pattern is based on the respective qualities of the step positions for the legs of the robot along the step path using the respective initial gait patterns.
15. The robot of claim 11 , wherein determining the adjusted step path is based on one or more step constraints.
16. The robot of claim 15 , wherein:
the one or more step constraints include:
one or more hard constraints that the adjusted step path cannot violate; and
one or more soft constraints, whereby each respective soft constraint of the one or more soft constraints is weighted based on a respective cost of the adjusted step path violating the respective soft constraint; and
determining the adjusted step path is based on the respective costs of the adjusted step path violating the respective soft constraints.
17. The robot of claim 16 , wherein:
the adjusted step path violates at least one of the one or more soft constraints; and
the respective cost corresponding to each violated soft constraint is less than a threshold cost.
18. The robot of claim 16 , wherein:
the adjusted step path violates at least one of the one or more soft constraints; and
a sum of the respective costs corresponding to each violated soft constraint is less than a threshold cost.
19. The robot of claim 15 , wherein the one or more step constraints comprise at least one of:
a threshold range of a center of pressure offset for each leg in contact with a ground surface, the center of pressure offset indicating an acceptable amount of robot weight distribution for each leg at each step position;
whether the adjusted step path causes a leg to step into a no-step region of the step-obstacle map;
whether the adjusted step path causes the body of the robot to enter a no-body region of the body-obstacle map;
whether the adjusted step path causes a self-collision of the robot; or
a margin of space about any no-step region of the step-obstacle map.
20. The robot of claim 11 , wherein the operations comprise determining, using the adjusted step path, an adjusted body path, the adjusted body path based on movement of the body of the robot as the legs of the robot travel along the adjusted step path.