cuArms: GPU-Accelerated Conflict-Based Planning for Multi-Arm Manipulation

Philip Huang; Fabio Ramos; Jiaoyang Li; Caelan Garrett; Lars Johannsmeier

cs.ROOct 26, 2026

cuArms: GPU-Accelerated Conflict-Based Planning for Multi-Arm Manipulation

Authors: Philip Huang, Fabio Ramos, Jiaoyang Li, Caelan Garrett, Lars Johannsmeier

Organizations: NVIDIA · Carnegie Mellon · University of Sydney

Abstract

Multi-arm manipulation has the potential to dramatically improve the throughput, efficiency, and dexterity of many manipulation tasks. Recent work coordinates multiple robot arms in a shared workcell by allocating and scheduling tasks for greater parallelism, jointly planning multi-arm motions, or directly learning multi-arm policies. So far, these approaches are either too slow, rely on domain-specific assumptions, or scale poorly with the number of robots and task horizon. Thus, we introduce cuArms, a conflict-based planner co-designed with GPU parallelism that efficiently decomposes the search space using reusable multi-modal roadmaps for individual robots and resolves conflicts and deadlocks through a lazy search. To jointly optimize task assignment, schedules, motions, and manipulation skills, we integrate a high-level scheduler that proposes candidate skeletons for cuArms to ground into coordinated manipulation plans. Experimental results show that our method establishes a new state of the art, with real-time initial solutions and anytime improvements in both motion quality and scheduling, without days of domain-specific training required by learning approaches. Videos of both simulated and real-world industrial tasks are available on https://cuarms.github.io/.

Figures & tables

Fig. 1 : Applications of cuArms : a) tabletop manipulation, b) welding, c) real object reorientation, and d) bimanual carry.

Fig. 2 : System and cuArms overview: A human or agent defines the task: the robots and their kinematics, the objects, goals, and constraints. The domain also supplies samplers that can generate feasible manipulation choices. A task scheduler, such as ScheduleStream, proposes a candidate schedule. This includes task assignment and ordering, along with satisfying samples such as placements, grasps, and inverse kinematic solutions. cuArms builds a per-robot multi-modal roadmap, searches for conflict-free robot movements and skills with GPU-batched conflict tables, and refines the solution trajectory with shortcutting. cuArms can iteratively replan with different schedule skeletons to improve upon infeasible or poor skeletons.

Fig. 3 : Example schedule skeletons in the four domains from Fig. 1 : (a) tabletop pick-and-place, (b) multi-robot reaching for welding, (c) bimanual handover, and (d) bimanual pick and coordinated carry. The high-level scheduler produces the skeleton with corresponding skill parameters such as handover poses, object placements, and grasp poses. cuArms then computes the coordinated multi-arm motions and skills based on the schedule skeleton.

Figure 4

Panel of Figure 5 — Fig. 5 : RoboBallet schedule search and refinement. Execution makespan improves as cuArms shortcuts initial trajectories and searches alternative schedules.

Targets	Robots	Method	Solved	$t_{\mathrm{offline}}(s)$	$t_{0}$ (s)	$J_{0}$ (s)	$J_{f}$ (s)
10	4	cuArms	150/150	0.81	0.20	10.61	5.64
40	4	cuArms	150/150	0.81	0.41	31.16	16.56
40	8	cuArms	150/150	1.74	0.87	25.35	14.87
10	4	RL	29/150	$1.6\times 10^{5}$	0.11	–	6.00
40	4	RL	50/150	$2.2\times 10^{5}$	0.42	–	24.25

TABLE II : RoboBallet scheduling and planning.

t_{\mathrm{offline}}

is the median base roadmap construction time for cuArms and training time for RL.

t_{0}

is the total inference time for RL.

	4 arms		8 arms
Targets	10	40	40
Greedy Scheduler	0.59	5.12	3.06
Roadmap Construction	98.70	155.39	271.17
Heuristics	47.68	120.81	146.44
Candidate Expansion & Sort	8.24	24.24	32.06
Conflict Table	22.46	65.94	277.46

TABLE III : cuArms median time-to-initial solution (ms) breakdown in RoboBallet. Roadmap construction refers to connecting new weld targets to the base roadmap. Collision checking includes queries in roadmap construction and the conflict table.

Panel of Figure 8 — Fig. 6 : Tabletop manipulation refinement. cuArms improves plans across skeletons and manipulation modes. Makespan can increase while the weighted optimization objective improves.

	cuArms				ScheduleStream
Task	Solved	$t_{0}$	$J_{0}$	$J_{f}$	Solved	$t_{0}$	$J_{0}$
Hold	45/45	0.48	5.46	2.37	44/45	1.75	3.74
Stack	45/45	2.26	12.84	6.67	38/45	4.02	16.11
Pack	45/45	2.96	12.02	6.96	38/45	4.54	17.45
Unpack	45/45	1.60	11.50	6.55	39/45	3.30	13.25

TABLE IV : Multi-arm TAMP for tabletop manipulation with two to four objects.

J_{0}

and

J_{f}

are the initial and final makespan, respectively.

Panel of Figure 10 — Fig. 7 : Scaling with number of objects. cuArms finds more efficient manipulation plans in less time than ScheduleStream, which also fails to find any solutions for 8-object packing.

Panel of Figure 11 — Fig. 8 : Bimanual Electronic Assembly Tasks with cuArms .

Multi-Robot Motion Planning

Multi-Robot Motion Planning coordinates collision-free paths and trajectories for robot teams sharing space, tasks, and changing environments.

See all 145 papers

VAMP-MR: Vector-Accelerated Motion Planning and Execution for Multi-Robot-Arms
Jul 15, 2026Philip Huang, Chenrui Gao, Jiaoyang LiMulti-Robot Motion Planning Robotic Manipulation
Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA · University of Michigan, Ann Arbor
P-ARC: Exploiting Subproblem Independence for Parallel Multi-Robot Motion Planning
Jun 26, 2026James D. Motes, Marco Morales, Nancy M. AmatoMulti-Robot Motion Planning Multi-Robot Coordination
Parasol Lab, School of Computing and Data Science, University of Illinois at Urbana Champaign, Champaign, IL, 61820 USA · Department of Computer Science at Instituto Tecnológico Autónomo de México (ITAM), Mexico City, México
Embodying Multi-Hand Manipulation Policies by Searching the Assignment and Null Spaces
Jul 24, 2026Yorai Shaoul, Jiaoyang Li, Maxim LikhachevMulti-Robot Motion Planning Constrained Motion Planning
The Robotics Institute, Carnegie Mellon University

Jul 15, 2026J/K move · Enter open · S save

VAMP-MR: Vector-Accelerated Motion Planning and Execution for Multi-Robot-Arms

Philip Huang, Chenrui Gao, Jiaoyang Li

Robotics Institute, Carnegie Mellon University, Pittsburgh, PA 15213, USA · University of Michigan, Ann Arbor

Multi-Robot Motion Planning Robotic Manipulation

Open paper AskPDF arXiv

Multi-robot-arm motion planning is a key challenge in deploying multiple manipulators for industrial tasks such as manufacturing. Existing search-based and sampling-based solvers often require significant computation time to produce collision-free, high-quality motions suitable for safe real-world execution. In this work, we introduce a new suite of multi-robot-arm motion planners capable of near real-time motion generation, combining classical planning algorithms with state-of-the-art vectorized collision-checking techniques. Based on CPU SIMD instructions, our new planners accelerate their primary bottleneck, collision checking, and achieve up to two orders of magnitude speedup in both motion planning and execution postprocessing for multi-arm manipulation tasks. We also release our implementation to lower the barrier for research and development of multi-robot-arm planning and manipulation problems. Code is available at https://vamp-mr.github.io/vamp-mr

Abstract

Multi-Robot Motion Planning

Explore similar work

VAMP-MR: Vector-Accelerated Motion Planning and Execution for Multi-Robot-Arms

P-ARC: Exploiting Subproblem Independence for Parallel Multi-Robot Motion Planning

Embodying Multi-Hand Manipulation Policies by Searching the Assignment and Null Spaces