Summary of Team IHMC's virtual robotics challenge entry

Koolen, Twan; Smith, Jesper; Thomas, Gray C.; Bertrand, Sylvain; Carff, John; Mertins, Nathan; Stephen, Douglas; Abeles, Peter; Englsberger, Johannes; McCrory, Stephen; Egmond, Jeff van; Griffioen, Maarten; Floyd, Marshall; Kobus, Samantha; Manor, Nolan; Alsheikh, Sami; Duran, Daniel; Bunch, Larry; Morphis, Eric; Colasanto, Luca; Hoang, Khai-Long Ho; Layton, Brooke; Neuhaus, Peter; Johnson, Matthew; Pratt, Jerry

doi:10.1109/humanoids.2013.7029992

Cited by 75 publications

(50 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Including an operator "in-the-loop," to help guide the robot through its goals without falling back on full teleoperation provides an alternative approach to accomplishing tasks where the robot and the operator can both employ their expertise as appropriate. This paradigm of shared autonomy has been studied for decades [6], [7] and has proven effective in recent robotics field experiments [8]- [10]. The PGP system presented here is a framework for shared autonomy for mobile manipulators that provides a significant amount of flexibility in both task specification and operation.…”

Section: Related Workmentioning

confidence: 98%

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: 98%

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

“…As will be discussed below, we use a redundant multiple-force description of the total wrench acting on a rigid body because it permits the use of simple linear friction constraints in our optimization. There has been compelling recent work in controlling the momenta of humanoids for balance and locomotion [40,45,32,38], including the resolved momentum control framework proposed by Kajita et al [37,53]. Inspired by this work, we design our planning algorithm using the concept of centroidal momentum.…”

Section: Dynamic Motion Planningmentioning

confidence: 99%

“…Several researchers have recently explored using QPs to control bipedal systems both in simulation [1,17,48,41,39,26] and in hardware [2,32,60,36]. As in our formulation, these optimizations typically employ low-dimensional dynamic quantities such as center of mass (COM) acceleration [1], rate of change of linear and angular momenta [48,32,39], zero moment point (ZMP) [60], or canonical walking functions [2], where the QP cost consists of a weighted distance from a reference value computed using a simple PD control rule [1,48,32].…”

Section: Additional Costs and Constraintsmentioning

confidence: 99%

Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot

et al. 2015

Self Cite

View full text Add to dashboard Cite

This paper describes a collection of optimization algorithms for achieving dynamic planning, control, and state estimation for a bipedal robot designed to operate reliably in complex environments. To make challenging locomotion tasks tractable, we describe several novel applications of convex, mixed-integer, and sparse nonlinear optimization to problems ranging from footstep placement to whole-body planning and control. We also present a state estimator formulation that, when combined with our walking controller, permits highly precise execution of extended walking plans over non-flat terrain. We describe our complete system integration and experiments carried out on Atlas, a full-size hydraulic humanoid robot built by Boston Dynamics, Inc.

show abstract

“…However, like ZMP-based criteria, it eschews the complex, joint-level dynamics of a full-body model, and summarizes the robot's dynamic state into a simple quantity, in this case its momenta. There has been a great success in controlling robots based on momenta [14] [13], including the resolved momentum control framework proposed by Kajita et. al.…”

Section: Introductionmentioning

confidence: 99%

Whole-body motion planning with centroidal dynamics and full kinematics

Dai¹,

Valenzuela²,

Tedrake³

2014

2014 IEEE-RAS International Conference on Humanoid Robots

379

290

View full text Add to dashboard Cite

Abstract-To plan dynamic, whole-body motions for robots, one conventionally faces the choice between a complex, fullbody dynamic model containing every link and actuator of the robot, or a highly simplified model of the robot as a point mass. In this paper we explore a powerful middle ground between these extremes. We exploit the fact that while the full dynamics of humanoid robots are complicated, their centroidal dynamics (the evolution of the angular momentum and the center of mass (COM) position) are much simpler. By treating the dynamics of the robot in centroidal form and directly optimizing the joint trajectories for the actuated degrees of freedom, we arrive at a method that enjoys simpler dynamics, while still having the expressiveness required to handle kinematic constraints such as collision avoidance or reaching to a target. We further require that the robot's COM and angular momentum as computed from the joint trajectories match those given by the centroidal dynamics. This ensures that the dynamics considered by our optimization are equivalent to the full dynamics of the robot, provided that the robot's actuators can supply sufficient torque. We demonstrate that this algorithm is capable of generating highly-dynamic motion plans with examples of a humanoid robot negotiating obstacle course elements and gait optimization for a quadrupedal robot. Additionally, we show that we can plan without pre-specifying the contact sequence by exploiting the complementarity conditions between contact forces and contact distance.

show abstract

Summary of Team IHMC's virtual robotics challenge entry

Cited by 75 publications

References 17 publications

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

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

Optimization-based locomotion planning, estimation, and control design for the atlas humanoid robot

Whole-body motion planning with centroidal dynamics and full kinematics

Contact Info

Product

Resources

About