Non-prehensile manipulation with mobile robots has primarily targeted placement in coarse goal regions. Precision placement has been studied with manipulators on benchmarks such as Push-T, where an omnidirectional end effector can readily re-approach an object from any side. For a mobile robot, correcting the same placement errors may require wide repositioning maneuvers around the object. We formalize multi-object pushing with a mobile robot as a multi-target assignment problem at tight tolerances. We propose a diffusion planner with a causal factorization: each robot denoising step is followed by an object step conditioned on the current clean robot estimate. This factorization allows us to sample multiple object outcomes for a single robot plan, capturing the multi-modality of pushing. We also design a set of pushing-specific costs for mobile robots, used for both guidance and best-of-N sampling at inference. On Push-T, our planner attains the highest success rate of the methods we compare, while having the lowest rate of implausible object motion. Across three multi-box pushing environments resembling warehouse scenarios, it raises the fraction of boxes placed by 21.5 percentage points over an unguided baseline, and replans 1.8× faster than a planner that denoises the two trajectories together. Lastly, we deploy the guided planner on a TurtleBot 3 Burger with object shapes absent from the training data, where it places 85.0% of objects within tolerance against Diffusion Policy's 37.5%.
Figures & tables
Fig. 1 : Robot completes a successful push during an Out-of-distribution (OOD) experiment with new shapes. Robot demo videos and code available on our project website
Fig. 2 : Architecture diagrams of the Joint prediction and Causal factorization planners. The Joint planner denoises both robot and object trajectories together. In contrast, the Causal planner makes two passes through a shared transformer decoder. The Robot phase runs first and Tweedie’s formula (Eq. ( 1 )) turns this output into a clean robot estimate τ^0R . The Object phase denoises τtO while being conditioned on τ^0R . The resulting chain τtR→τ^0R→τ^0O is differentiable through both decoder passes.
Term
Role
Penalty
Cplace⋆
Push
Asymmetric endpoint error along the push axis (overshoot =25× undershoot) plus squared lateral error. Object endpoint near target.
Cpred⋆
Push
Penalizes the object’s predicted landing position at the horizon end, assuming it keeps its current along-axis velocity. Lookahead to predict overshoot.
Ccoll(o)
Safety
Margin violation of the predicted object trajectory against placed objects and obstacles, through the barrier Ψ(x)=ex−x−1 . Object penetrates margin.
Ccoll(r)
Safety
Same barrier on the predicted robot trajectory. Robot penetrates margin.
Cretreat⋆
Retreat
Penalizes robot proximity to the target object when retreat is needed. Bad approach, or target object is placed.
TABLE I : Summary of the five guidance cost terms. Starred ( ⋆ ) terms are novel contributions of this work, while the rest are inspired by [ 18 ] . Each penalty is followed in italics by the condition under which it is active.
TABLE II : Push-T simulation results with each method at its own best-of- N draws per replan, selected by success rate over N∈{1,8,16,32} : N=16 for Diffusion Forcing [100 DDIM] and Joint [100 DDIM], N=32 for Causal [100 DDIM], and N=8 for Causal [50 DDIM]. Causal consistently has the highest success rate across all batch sizes. Each row pools 75 episodes ( 25 episodes ×3 seeds: 42 , 1000 , 2000 ). Max and Final are reported with their 95% confidence intervals (CI), and SR with its Wilson 95% CI. Latency is roughly constant across the different batch sizes for each model. All models have around 17.8 M parameters. Rows are color-coded: baselines , ablations , ours (proposed) . Bolded entries mark the best per column.
TABLE III : Simulation results across 3 previously unseen environments at two goal tolerances ( 4 cm, 2 cm), pooled over 150 episodes per cell ( 3 seeds ×50 episodes). All diffusion methods used 100 DDIM steps, unless otherwise stated, and are trained at a tolerance of 2 cm. Diffusion Policy uses FiLM [ 30 ] for conditioning whereas Joint and Causal use AdaLN [ 26 ] . For best of N sampling, the sample that minimizes the cost function in Sec. IV-D is selected. SPL and BPF are both reported out of 100 and with their 95% CIs. Bolded entries mark the best BPF per (environment, tolerance). Causal w/ MC DPS is run at K=16 . Rows are color-coded: baselines , ablations , ours (proposed) .
Recent advances in robotic manipulation have highlighted the effectiveness of learning from demonstration. However, while end-to-end policies excel in expressivity and flexibility, they struggle both in generalizing to novel object geometries and in attaining a high degree of precision. An alternative, object-centric approach frames the task as predicting the placement pose of the target object, providing a modular decomposition of the problem. Building on this goal-prediction paradigm, we propose TAX-DPD, a hierarchical, disentangled point diffusion framework that achieves state-of-the-art performance in placement precision, multi-modal coverage, and generalization to variations in object geometries and scene configurations. We model global scene-level placements through a novel feed-forward Dense Gaussian Mixture Model (GMM) that yields a spatially dense prior over global placements; we then model the local object-level configuration through a novel disentangled point cloud diffusion module that separately diffuses the object geometry and the placement frame, enabling precise local geometric reasoning. Interestingly, we demonstrate that our point cloud diffusion achieves substantially higher accuracy than a prior approach based on SE(3)-diffusion, even in the context of rigid object placement. We validate our approach across a suite of challenging tasks in simulation and in the real-world on high-precision industrial insertion tasks. Furthermore, we present results on a cloth-hanging task in simulation, indicating that our framework can further relax assumptions on object rigidity.
Lyuxing He, Eric Cai, Shobhit Aggarwal +2
The authors are with Carnegie Mellon University, Pittsburgh, USA. · The author is with ABB Inc., USA.
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
Motion planning often admits multiple feasible solutions, making multimodal generation valuable, particularly for flexible multi-robot coordination. Diffusion models naturally learn such trajectory distributions, yet incorporating coarse and partial trajectory priors without restricting generation remains challenging. Such priors indicate a desirable region of the solution space rather than a single solution, motivating conditioned generation that preserves multimodality. In this paper, we guide trajectory generation in the clean trajectory space and progressively incorporate trajectory priors with a timestep-dependent guidance strength. At each reverse diffusion step, the reconstructed clean trajectory provides a unified space for integrating planning costs and partial trajectory priors. Planning costs are incorporated through gradient-based refinement, while the partial prior is progressively injected at the corresponding noise levels with decreasing guidance strength. This guides generation toward the prior in early stages while gradually releasing the constraint to preserve the inherent multimodality of the diffusion model. The framework naturally extends to multi-robot planning by incorporating inter-robot collision costs. Experiments on single- and multi-robot planning tasks demonstrate controllable trajectory synthesis, diverse feasible solutions, and safe multi-agent coordination.
Tianyou Yu, Shengze Cai, Chao Xu
Institute of Cyber-System and Control, College of Control Science and Engineering, Zhejiang University, Hangzhou 310027, China