Pith. sign in

REVIEW 8 cited by

PlasticineLab: A Soft-Body Manipulation Benchmark with Differentiable Physics

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2104.03311 v1 pith:RK25724U submitted 2021-04-07 cs.LG cs.AIcs.CVcs.GRcs.RO

classification cs.LGcs.AIcs.CVcs.GRcs.RO
keywords physicsdifferentiabletasksbenchmarklearningalgorithmsapproachesbody
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Simulated virtual environments serve as one of the main driving forces behind developing and evaluating skill learning algorithms. However, existing environments typically only simulate rigid body physics. Additionally, the simulation process usually does not provide gradients that might be useful for planning and control optimizations. We introduce a new differentiable physics benchmark called PasticineLab, which includes a diverse collection of soft body manipulation tasks. In each task, the agent uses manipulators to deform the plasticine into the desired configuration. The underlying physics engine supports differentiable elastic and plastic deformation using the DiffTaichi system, posing many under-explored challenges to robotic agents. We evaluate several existing reinforcement learning (RL) methods and gradient-based methods on this benchmark. Experimental results suggest that 1) RL-based approaches struggle to solve most of the tasks efficiently; 2) gradient-based approaches, by optimizing open-loop control sequences with the built-in differentiable physics engine, can rapidly find a solution within tens of iterations, but still fall short on multi-stage tasks that require long-term planning. We expect that PlasticineLab will encourage the development of novel algorithms that combine differentiable physics and RL for more complex physics-based skill learning tasks.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Learning Physics-Guided Residual Dynamics for Deformable Object Simulation

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Physics-guided residual dynamics, a spring-mass simulator plus a network that predicts velocity corrections, yields the most accurate deformable-object simulation in the paper's real-world tests.

  2. SoftVTBench: A Safety-Aware Visuo-Tactile Benchmark for Physically Constrained Robotic Manipulation of Deformable Objects

    cs.RO 2026-07 conditional novelty 6.0 of 10

    Success-only metrics overstate deformable-manipulation performance; tactile sensing raises Safety Success (e.g. 21.4%→35.6% on Object-Soft) while Goal Success stays comparable.

  3. Genie Sim 3.0 : A High-Fidelity Comprehensive Simulation Platform for Humanoid Robot

    cs.RO 2026-01 unverdicted novelty 6.0 of 10

    Genie Sim 3.0 introduces an LLM-powered scene generator, the first LLM-based automated evaluation benchmark, and a large open synthetic dataset that demonstrates zero-shot sim-to-real transfer for robotic manipulation...

  4. Robust and Efficient MuJoCo-based Model Predictive Control via Web of Affine Spaces Derivatives

    cs.RO 2025-12 conditional novelty 6.0 of 10

    WASP derivative reuse speeds up MuJoCo MPC by 1.26–2.08x versus finite differences on selected locomotion tasks, with comparable task costs.

  5. Hybrid Neural-MPM for Interactive Fluid Simulations in Real-Time

    cs.LG 2025-05 conditional novelty 6.0 of 10

    A hybrid neural-MPM solver with a chaos-triggered fallback and a diffusion-based sketch controller enables real-time interactive fluid simulation with user control.

  6. Manipulating Elasto-Plastic Objects With 3D Occupancy and Learning-Based Predictive Control

    cs.RO 2025-05 conditional novelty 6.0 of 10

    3D occupancy representation with a learned 3D CNN-GNN dynamics model and MPC enables a robot to shape plasticine into letter goals in both simulation and the real world.

  7. Data Pyramid for Embodied Manipulation

    cs.RO 2026-07 conditional novelty 3.0 of 10

    Embodied training data form a five-layer pyramid—real-robot, UMI, ego/exo, simulation, general V–L—ordered by the trade-off between scale and robot alignment, and model capabilities track how those layers are mixed.

  8. From 2D to 3D Cognition: A Brief Survey of General World Models

    cs.CV 2025-06 conditional novelty 3.0 of 10

    A survey proposing a two-pillar, three-capability framework that organizes recent AI world models by their transition from 2D visual prediction to 3D cognition.

Pith tools