Pith. sign in

REVIEW 15 cited by

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

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 2209.05451 v2 pith:7P3DAJLS submitted 2022-09-12 cs.RO cs.AIcs.CLcs.CVcs.LG

Perceiver-Actor: A Multi-Task Transformer for Robotic Manipulation

classification cs.RO cs.AIcs.CLcs.CVcs.LG
keywords manipulationmulti-taskperacttaskstransformeractionactionsformulation
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Transformers have revolutionized vision and natural language processing with their ability to scale with large datasets. But in robotic manipulation, data is both limited and expensive. Can manipulation still benefit from Transformers with the right problem formulation? We investigate this question with PerAct, a language-conditioned behavior-cloning agent for multi-task 6-DoF manipulation. PerAct encodes language goals and RGB-D voxel observations with a Perceiver Transformer, and outputs discretized actions by ``detecting the next best voxel action''. Unlike frameworks that operate on 2D images, the voxelized 3D observation and action space provides a strong structural prior for efficiently learning 6-DoF actions. With this formulation, we train a single multi-task Transformer for 18 RLBench tasks (with 249 variations) and 7 real-world tasks (with 18 variations) from just a few demonstrations per task. Our results show that PerAct significantly outperforms unstructured image-to-action agents and 3D ConvNet baselines for a wide range of tabletop tasks.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 15 Pith papers

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

  1. Learning to See While Learning to Act: Diffusion Models for Active Perception in Robot Imitation

    cs.RO 2026-06 unverdicted novelty 7.0

    See2Act couples action denoising with viewpoint refinement in a diffusion-based imitation learning policy trained on keyframe-anchored camera poses, recovering informative views under occlusion and improving RLBench p...

  2. OA-WAM: Object-Addressable World Action Model for Robust Robot Manipulation

    cs.RO 2026-05 unverdicted novelty 7.0

    OA-WAM uses persistent address vectors and dynamic content vectors in object slots to enable addressable world-action prediction, improving robustness on manipulation benchmarks under scene changes.

  3. Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

    cs.RO 2023-04 conditional novelty 7.0

    Low-cost imprecise robots achieve 80-90% success on six fine bimanual manipulation tasks using imitation learning with a new Action Chunking with Transformers algorithm trained on only 10 minutes of demonstrations.

  4. Geometry-Aware Motion Latents for Learning Robust Manipulation Policies

    cs.RO 2026-07 conditional novelty 6.0

    Predicting future 3D pointmaps forces discrete motion latents to encode physical geometric transformations, improving single-view robot manipulation over 2D/static-3D baselines.

  5. See Less, Specify More: Visual Evidence Budgets for Generalizable VLAs

    cs.RO 2026-06 unverdicted novelty 6.0

    S2 improves generalization in vision-language-action models by using goal-preserving refined language guidance and explicit visual evidence budgets, raising mean subtask success from 54.2% to 79.0% on eight real-robot...

  6. LLM-Guided Future Hypotheses for Horizon-Aware Exploration in Multi-Step Robot Manipulation

    cs.RO 2026-05 unverdicted novelty 6.0

    FEC conditions policies on LLM-guided short-horizon future videos via a three-stage pipeline, yielding performance gains for BC+RL over no-future baselines on RoboCasa and CALVIN while mismatched futures degrade results.

  7. SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation

    cs.RO 2026-03 conditional novelty 6.0

    Adding a recurrent, gated cross-attention memory to Diffusion Policy improves long-horizon robot manipulation success by keeping a compact evolving state instead of stacking more observation frames.

  8. SeedPolicy: Horizon Scaling via Self-Evolving Diffusion Policy for Robot Manipulation

    cs.RO 2026-03 conditional novelty 6.0

    SeedPolicy introduces self-evolving gated attention to extend the temporal horizon of diffusion policies, yielding 36.8% and 169% relative gains over standard DP on clean and randomized RoboTwin 2.0 tasks.

  9. GAF: Gaussian Action Field as a 4D Representation for Dynamic World Modeling in Robotic Manipulation

    cs.RO 2025-06 unverdicted novelty 6.0

    GAF creates 4D dynamic scene models by adding motion to 3D Gaussians, enabling better reconstruction and 7.3% higher success in robotic tasks.

  10. Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperation

    cs.RO 2024-01 conditional novelty 6.0

    A low-cost whole-body teleoperation system enables effective imitation learning for complex bimanual mobile manipulation by co-training on mobile and static demonstration datasets.

  11. PaLM-E: An Embodied Multimodal Language Model

    cs.LG 2023-03 conditional novelty 6.0

    PaLM-E is a single 562B-parameter multimodal model that performs embodied reasoning tasks like robotic manipulation planning and visual question answering by interleaving vision, state, and text inputs with positive t...

  12. Scaling Robot Learning with Semantically Imagined Experience

    cs.RO 2023-02 unverdicted novelty 6.0

    Augmenting robot datasets via diffusion-based semantic inpainting enables manipulation policies to solve unseen tasks with new objects and improves robustness to novel distractors.

  13. Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies

    cs.RO 2026-07 conditional novelty 5.5

    Q-guided reverse-time flow sampling with a rollout-trained action-chunk critic improves frozen SmolVLA success on LIBERO, with strong single-task gains but only modest locked held-out transfer.

  14. DIPOLE: Fusing Vision and Geometry for Robust Visuomotor Generalization

    cs.RO 2025-11 conditional novelty 5.0

    Fusing RGB and point-cloud inputs with training-time modality dropout plus cross-attention makes a diffusion visuomotor policy markedly more robust to visual and spatial shifts than unimodal or naively fused baselines.

  15. Guided Action Flow: Q-Guided Inference for Flow-Matching Vision-Language-Action Policies

    cs.RO 2026-07 unverdicted novelty 4.0

    Guided Action Flow applies a rollout-trained critic to steer frozen flow-matching VLA policies at inference time via action gradients, reporting success rate gains on LIBERO manipulation tasks.