The reviewed record of science sign in
Pith

arxiv: 2410.05273 · v3 · pith:5BWHFRB7 · submitted 2024-09-12 · cs.CV · cs.AI· cs.RO

HiRT: Enhancing Robotic Control with Hierarchical Robot Transformers

Reviewed by Pithpith:5BWHFRB7open to challenge →

classification cs.CV cs.AIcs.RO
keywords hirttaskscontrolmodelssuccessbackendsdynamicfeatures
0
0 comments X
read the original abstract

Large Vision-Language-Action (VLA) models, leveraging powerful pre trained Vision-Language Models (VLMs) backends, have shown promise in robotic control due to their impressive generalization ability. However, the success comes at a cost. Their reliance on VLM backends with billions of parameters leads to high computational costs and inference latency, limiting the testing scenarios to mainly quasi-static tasks and hindering performance in dynamic tasks requiring rapid interactions. To address these limitations, this paper proposes HiRT, a Hierarchical Robot Transformer framework that enables flexible frequency and performance trade-off. HiRT keeps VLMs running at low frequencies to capture temporarily invariant features while enabling real-time interaction through a high-frequency vision-based policy guided by the slowly updated features. Experiment results in both simulation and real-world settings demonstrate significant improvements over baseline methods. Empirically, in static tasks, we double the control frequency and achieve comparable success rates. Additionally, on novel real-world dynamic ma nipulation tasks which are challenging for previous VLA models, HiRT improves the success rate from 48% to 75%.

This paper has not been read by Pith yet.

discussion (0)

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

Forward citations

Cited by 9 Pith papers

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

  1. Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models

    cs.RO 2026-05 unverdicted novelty 7.0

    Pace-and-Path Correction decomposes a quadratic cost minimization into orthogonal pace and path channels to correct chunked actions in VLA models, raising success rates by up to 28.8% in dynamic settings.

  2. ROSA: A Robotics Foundation Model Serving System for Robot Factories

    cs.RO 2026-07 unverdicted novelty 6.0

    ROSA introduces shared GPU-pool serving, robotics-aware abstractions for multi-model pipelines, and factory-productivity scheduling that improves output by up to 12.06x over dedicated per-robot systems.

  3. ROAD-VLA: Robust Online Adaptation via Self-Distillation for Vision-Language-Action Models

    cs.LG 2026-06 unverdicted novelty 6.0

    ROAD-VLA constructs an advantage-perturbed proximal teacher in action space to convert sparse rewards into dense supervision for online VLA adaptation and reports outperformance versus PPO across seven manipulation en...

  4. UniFS: Unified Fast-to-Slow Hierarchical Architecture for Vision-Language-Action Models

    cs.RO 2026-06 unverdicted novelty 6.0

    UniFS achieves 98.3% success on LIBERO with 2.1x lower latency than prior fast-slow VLA models by stratifying VLM layer update frequencies, inverting latent interactions, and applying multi-level supervision.

  5. Overcoming Dynamics-Blindness: Training-Free Pace-and-Path Correction for VLA Models

    cs.RO 2026-05 unverdicted novelty 6.0

    Pace-and-Path Correction is a closed-form inference-time operator that decomposes a quadratic cost minimization into orthogonal pace compression and path offset channels to correct dynamics-blindness in chunked-action...

  6. Veo-Act: How Far Can Frontier Video Models Advance Generalizable Robot Manipulation?

    cs.RO 2026-04 unverdicted novelty 6.0

    Veo-3 video predictions enable approximate task-level robot trajectories in zero-shot settings but require hierarchical integration with low-level VLA policies for reliable manipulation performance.

  7. Ctrl-World: A Controllable Generative World Model for Robot Manipulation

    cs.RO 2025-10 unverdicted novelty 6.0

    A controllable world model trained on the DROID dataset generates consistent multi-view robot trajectories for over 20 seconds and improves generalist policy success rates by 44.7% via imagined trajectory fine-tuning.

  8. Video Prediction Policy: A Generalist Robot Policy with Predictive Visual Representations

    cs.CV 2024-12 unverdicted novelty 6.0

    Video Prediction Policy conditions robot action learning on future-frame predictions inside fine-tuned video diffusion models, yielding 18.6% relative gains on Calvin ABC-D and 31.6% higher real-world success rates.

  9. Cortex: A Bidirectionally Aligned Embodied Agent Framework for Long-horizon Manipulation

    cs.RO 2026-07 conditional novelty 5.0

    A dual-system framework with a structured subtask interface, event-balanced training, and inference harness enables VLM-guided long-horizon robotic manipulation, achieving 95.5% on LIBERO-Long and 65% on real-world ch...