Stance selection for humanoid grasping tasks by inverse reachability maps

Burget, Felix; Bennewitz, Maren

doi:10.1109/icra.2015.7139993

Cited by 36 publications

(33 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Determining a stance location that brings a robot's end effector to a desired location has been also investigated. Brurget et al create inverse reachability maps that allow a robot to rank stance locations by the condition of the robot's manipulator at the grasping pose [4]. Stulp et al introduced ActionRelated Places (ARPlace) that represent a probability mapping over locations where the target object could be successfully grasped given the positions of the target object and the robot [5].…”

Section: Related Workmentioning

confidence: 99%

Prophetic goal-space planning for human-in-the-loop mobile manipulation

James¹,

Weng²,

Hart

et al. 2015

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

This paper introduces the Prophetic Goal-Space Planner (PGP) system developed to accomplish mobile manipulation tasks. Goal-space planning exploits the under-constrained and variable nature of many real-world tasks by defining Cartesian goals in terms of intuitive solution manifolds (e.g., the principal axis of a cylindrical handle, the rim of a valve, the surface of a step) rather than precise points in 6-dimensional space. The PGP system combines 1) a goal-space planner, 2) a kinematic planner and visualizer called the prophet, and 3) user interface tools. The prophet determines appropriate stance locations for the robot to reach its goals and animates the result. The UI tools allow a human operator to either approve or reject the planner's output (the "prophecy"), request new plans, or adjust the goal-space target regions to better match the robot's perceived environment. The PGP system thus enables a level of shared autonomy between the robot and operator that can ensure task completion with only limited, corrective operator input. PGP was employed by Team TRACLabs on the Boston Dynamics Atlas robot for the DARPA Robotics Challenge (DRC) 2015 Finals. PGP enabled the efficient completion of multiple manipulation tasks, including opening and walking through a door, walking up to and turning a valve, and throwing a lever-despite degraded network communication channelsand contributed to TRACLabs' placing 9th out of 23 teams in the competition.

show abstract

Section: Related Workmentioning

confidence: 99%

Prophetic goal-space planning for human-in-the-loop mobile manipulation

James¹,

Weng²,

Hart

et al. 2015

2015 IEEE-RAS 15th International Conference on Humanoid Robots (Humanoids)

View full text Add to dashboard Cite

show abstract

“…This is in contrast with the prior work [10], [11] which limited the foot poses to a constant distance and planning for the mid-feet point. A supplementary video can be found at https://youtu.be/o-05EHf-gg8.…”

Section: Hardware Experimentsmentioning

confidence: 88%

“…Collisions have to be checked online. This was applied to a humanoid robot to find SE(2) (flat terrain) stance locations which vastly improves the success rate for humanoid manipulation [10]. Yang et al [11] proposed the inverse dynamic reachability map (iDRM) in which the IRM was extended by utilizing a configuration-to-workspace occupation mapping [12] to enable efficient collision updates.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Efficient Humanoid Motion Planning on Uneven Terrain Using Paired Forward-Inverse Dynamic Reachability Maps

Yang

Merkt

Ferrolho

et al. 2017

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Abstract-A key prerequisite for planning manipulation with locomotion of humanoid robots in complex environments is to find a valid end-pose with a stable stance location and a collisionfree, balanced full-body configuration. Prior work based on the Inverse Reachability Map assumed that the feet are placed next to each other around the stance location on a horizontal plane. Additionally, the success rate was correlated with the coverage density of the sampled space, which is in turn limited by the memory needed for storing the map.We present a Paired Forward-Inverse Dynamic Reachability Maps that extends the inverse Dynamic Reachability Map (iDRM) by integrating it with forward reachability maps according to the inherent kinematic structure of the robot. By exploiting the combinatorics of this modularity, greater coverage in each map can be achieved while keeping a low number of stored samples. This enables us to draw samples from a much richer dataset to effectively plan end-poses for single-handed as well as bimanual tasks on uneven terrain. We demonstrated the method on the 38-DoF NASA Valkyrie humanoid utilizing the whole body to exploit redundancy for accomplishing manipulation tasks on uneven terrain while avoiding obstacles.

show abstract

“…Initial work on path planning and reachability was typically performed for simple grasp points on objects [1], which involves creating a map representing the areas of high dexterity for the manipulators. This work was then extended to the use of reachability maps to solve the inverse reachability task [2] and [3], where the optimal base placement was found in order to perform the desired grasp on an object. Work done by [4] examined ways to simplify the reachability map by generating a capability map, a simplified structure that permits faster and more efficient searches of the map in order to solve the inverse reachability problem.…”

Section: Related Workmentioning

confidence: 99%

Reuleaux: Robot Base Placement by Reachability Analysis

Makhal

Goins²

2018

2018 Second IEEE International Conference on Robotic Computing (IRC)

View full text Add to dashboard Cite

Before beginning any robot task, users must position the robot's base, a task that now depends entirely on user intuition. While slight perturbation is tolerable for robots with moveable bases, correcting the problem is imperative for fixedbase robots if some essential task sections are out of reach. For mobile manipulation robots, it is necessary to decide on a specific base position before beginning manipulation tasks. This paper presents Reuleaux, an open source library for robot reachability analyses and base placement. It reduces the amount of extra repositioning and removes the manual work of identifying potential base locations. Based on the reachability map, base placement locations of a whole robot or only the arm can be efficiently determined. This can be applied to both statically mounted robots, where position of the robot and work piece ensure the maximum amount of work performed, and to mobile robots, where the maximum amount of workable area can be reached. Solutions are not limited only to vertically constrained placement, since complicated robotics tasks require the base to be placed at unique poses based on task demand.All Reuleaux library methods were tested on different robots of different specifications and evaluated for tasks in simulation and real world environment. Evaluation results indicate that Reuleaux had significantly improved performance than prior existing methods in terms of time-efficiency and range of applicability.

show abstract

Stance selection for humanoid grasping tasks by inverse reachability maps

Cited by 36 publications

References 13 publications

Prophetic goal-space planning for human-in-the-loop mobile manipulation

Prophetic goal-space planning for human-in-the-loop mobile manipulation

Efficient Humanoid Motion Planning on Uneven Terrain Using Paired Forward-Inverse Dynamic Reachability Maps

Reuleaux: Robot Base Placement by Reachability Analysis

Contact Info

Product

Resources

About