Object rearrangement in cluttered tabletop scenes is challenging, especially in wide workspaces where dual-arm systems improve coverage and efficiency. Limited free space often necessitates buffering, while objects near or across the shared reachability region of the manipulators must be transferred under careful coordination to avoid inter-arm collisions. Conventional inter-arm transfer typically relies on a fixed handoff configuration, which constrains where and how objects are exchanged, enforces spatiotemporal synchronization of the arms, and reduces flexibility in dense layouts. This paper presents a dual-arm rearrangement framework that combines movable stacking with Gap-Aware Push Transfer for asynchronous cross-boundary exchange. The method scans the shared boundary to identify collision-free transfer gaps, places an object near a selected crossing point, and then pushes it into the receiving workspace without requiring simultaneous interaction between the two arms. A joint Monte Carlo Tree Search (MCTS)-based planner coordinates both manipulators while reasoning over buffering and transfer decisions, and execution cost is used after planning to assess the resulting plan. Experiments show that the proposed method shortens joint execution sequences and becomes increasingly advantageous over a fixed handoff baseline as scene density increases, achieving lower execution cost in denser scenes while remaining competitive in lighter ones.
Figures & tables
Fig. 1 : Overview of the proposed dual-arm rearrangement framework, where temporary stacks are formed near the shared boundary for movable stacking [ 4 ] , and objects are transferred between workspaces.
Fig. 2 : Illustration of a fixed aerial handoff configuration for inter-arm transfer in dual-arm rearrangement, adapted from [ 7 ] .
Fig. 3 : Asynchronous cross-boundary push transfer (proposed method) versus synchronous fixed handoff.
Reference
Robot Setup
Planning Backbone
Buffering Model
Inter-arm Exchange / Transfer
Gao et al. [ 7 ]
Dual-arm
Task planning
Lazy buffers
Predefined handoff pose
Shome et al. [ 9 ]
Dual-arm
Mixed-integer optimization
Monotone (no intermediate buffering)
Synchronous paired transfers
Li et al. [ 16 ]
Dual-arm
Cooperative mTSP + RL
Monotone (no temporal buffering)
Shared-workspace synchronized actions
Gao et al. [ 17 ]
Dual-arm
Integrated TAMP + trajectory optimization
Lazy buffers
Predefined handoff pose
Barghi et al. [ 4 ]
Single-arm
A* + MCTS goal-attempting
Movable stacking
N/A
Proposed
Dual-arm
Joint MCTS
Movable stacking
Gap-Aware Push Transfer
TABLE I : Qualitative comparison of representative rearrangement frameworks in terms of robot setup, planning backbone, buffering model, and inter-arm exchange/transfer mechanism.
Fig. 4 : Overview of the proposed dual-arm rearrangement framework, from initial and target scenes to coordinated dual-arm planning and execution. The figure also shows the primitive actions— move , stack , push , and wait —that form the basic operations for object manipulation and inter-arm coordination.
Fig. 5 : Conceptual comparison between a fixed-handoff transfer scheme with a predefined transfer pose [ 7 ] and the proposed method. The fixed point is illustrative, highlighting that the handoff location is predetermined rather than selected online.
Fig. 6 : Selection of the crossing row from feasible free intervals along the boundary strip.
N
Strategy
Joint Steps
Execution Cost
5
Fixed Handoff [ 7 ]
6.67
9.63
Proposed (Gap-Aware Push Transfer)
6.60
9.96
6
Fixed Handoff [ 7 ]
8.00
11.73
Proposed (Gap-Aware Push Transfer)
7.98
12.47
7
Fixed Handoff [ 7 ]
10.58
16.15
Proposed (Gap-Aware Push Transfer)
9.93
15.96
TABLE II : Benchmark results for the compared methods under increasing scene density. The advantage of the proposed strategy becomes more pronounced in denser scenes.
Fig. 7 : Performance comparison of two MCTS-based strategies across varying object counts. Bars represent mean values with confidence intervals. The proposed method demonstrates a clearer advantage over the Fixed Handoff baseline.
We devise a dual-arm cooperative planning framework for wiping table surface in the presence of scattered objects. Unlike conventional surface-cleaning strategies that only cover free areas and detour around obstacles, our framework explicitly assigns one arm to rearrange objects while the other performs coverage wiping, thereby enabling access to previously obstructed regions. Specifically, we first construct a set of wiping and object-rearrangement action primitives. Based on these primitives, we introduce Geo-MILP, a geometry-aware task planner formulated as Mixed-Integer Linear Programming (MILP). By integrating Logic-Based Benders Decomposition (LBBD), Geo-MILP iteratively optimizes action sequencingand timing to resolve geometric conflicts, promoting efficient cooperation between wiping and object rearrangement. We then employ K-Order Markov Optimization (KOMO) to generate smooth, collision-free motions to ensure feasible execution. Simulation and physical experiments demonstrate that the proposed framework not only increases reachable coverage by enabling access to obstructed areas, but also significantly improves time efficiency compared to Task and Motion Planning (TAMP) baselines, reducing planning time by up to 9 times and execution makespan by approximately 40%.
Pengqi Zhang, Longchang Yu, Daohan Li +2
School of Automation Science and Electrical Engineering, Beihang University · Beijing Institute for General Artificial Intelligence (BIGAI) · Delta Intelligence +1
We focus on the problem of rearranging multiple objects within a constrained workspace via pushing using a team of car-like robots. While the use of multiple robots offers the potential for more efficient execution, the need for conflict resolution and the kinematic constraints arising from physics, robot design, and the workspace boundary make this problem especially challenging. Our key insight is that by exploiting the structure introduced by the car-like kinematics of the domain, we could relax the problem into an ordered assignment of Dubins curves to robots. To this end, we introduce MultiPush, a reinforcement-learning based framework that jointly determines an efficient schedule of pushing tasks and their allocation to available robots by leveraging a constraint-aware traversability graph. Across extensive simulated trials with up to 14 objects and teams of two to four robots, MultiPush reduces the makespan by up to 16% compared to the baselines while requiring up to 2.9 times faster planning time. We demonstrate MultiPush on a real-world scenario involving the rearrangement of 12 objects by two and three robots (1/10-scale racecars) in a constrained space.
Jeeho Ahn, Christoforos Mavrogiannis
Robotics Department, University of Michigan, Ann Arbor, USA
Object rearrangement planning in cluttered environments is often non-monotone, requiring objects to be temporarily relocated before reaching their final destinations. Although search-based planners can solve such tasks, they incur substantial computational cost and require expensive replanning when the environment changes. We propose the Visual Adaptive Rearrangement Planner (VARP), which learns non-monotone rearrangement directly from visual state representations generated from expert demonstrations. VARP predicts pick-and-place actions from the current and goal visual state representations, and incorporates an Action Refinement Strategy (ARS) to improve action feasibility and a Progress Enforcement Strategy (PES) to mitigate progress stagnation. By continuously updating actions from the latest visual state representations, VARP adapts online to disturbances without replanning from scratch or performing online combinatorial search. In challenging rearrangement benchmarks, VARP achieves a 98.3% success rate with only 0.4 s planning time per task, 97.5% success under execution-time disturbances, and 94.5% under continuous severe disturbances, while generalizing effectively to unseen object counts. These results demonstrate that VARP provides a scalable and robust solution for non-monotone object rearrangement.