Pith. sign in

REVIEW 5 cited by

Human-Object Interaction from Human-Level Instructions

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 2406.17840 v3 pith:WSZHRSG6 submitted 2024-06-25 cs.AI cs.CV

classification cs.AIcs.CV
keywords instructionsenvironmentshuman-levelinteractionssystemdetailedhuman-objectinteraction
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Intelligent agents must autonomously interact with the environments to perform daily tasks based on human-level instructions. They need a foundational understanding of the world to accurately interpret these instructions, along with precise low-level movement and interaction skills to execute the derived actions. In this work, we propose the first complete system for synthesizing physically plausible, long-horizon human-object interactions for object manipulation in contextual environments, driven by human-level instructions. We leverage large language models (LLMs) to interpret the input instructions into detailed execution plans. Unlike prior work, our system is capable of generating detailed finger-object interactions, in seamless coordination with full-body movements. We also train a policy to track generated motions in physics simulation via reinforcement learning (RL) to ensure physical plausibility of the motion. Our experiments demonstrate the effectiveness of our system in synthesizing realistic interactions with diverse objects in complex environments, highlighting its potential for real-world applications.

Discussion (0). Sign in to comment.

Forward citations

Cited by 5 Pith papers

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

  1. OmniRetarget: Interaction-Preserving Data Generation for Humanoid Whole-Body Loco-Manipulation and Scene Interaction

    cs.RO 2025-09 conditional novelty 6.0 of 10

    An interaction-mesh retargeting pipeline with hard constraints generates robot training references that preserve object/terrain contacts, enabling long-horizon humanoid loco-manipulation with minimal rewards.

  2. InterAct: Advancing Large-Scale Versatile 3D Human-Object Interaction Generation

    cs.CV 2025-09 conditional novelty 6.0 of 10

    InterAct is a unified 21.81-hour 3D human-object interaction benchmark with text annotations, quality-corrected data, and a multi-task model that achieves state-of-the-art results across six generation tasks.

  3. GenHOI: Generalizing Text-driven 4D Human-Object Interaction Synthesis for Unseen Objects

    cs.CV 2025-06 conditional novelty 6.0 of 10

    GenHOI generates 4D human-object interaction sequences for unseen objects by predicting sparse 3D keyframes and interpolating them with a contact-aware diffusion model.

  4. CoDA: Coordinated Diffusion Noise Optimization for Whole-Body Manipulation of Articulated Objects

    cs.GR 2025-05 conditional novelty 6.0 of 10

    CoDA generates coordinated whole-body articulated-object manipulation by optimizing the noise of three decoupled diffusion models, guided by BPS-based end-effector and object trajectories.

  5. Half-Physics: Enabling Kinematic 3D Human Model with Physical Interactions

    cs.CV 2025-07 conditional novelty 5.0 of 10

    Half physics converts kinematic SMPL-X poses into velocities that drive a physics engine, preserving the original motion when contact-free and giving physically correct responses when collisions occur.

Pith tools