Pith. sign in

REVIEW 8 cited by

AnyCar to Anywhere: Learning Universal Dynamics Model for Agile and Adaptive Mobility

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 2409.15783 v1 pith:ICBCXXYK submitted 2024-09-24 cs.RO

classification cs.RO
keywords modelagileacrossanycarcontrolmodelsrobotvarious
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Recent works in the robot learning community have successfully introduced generalist models capable of controlling various robot embodiments across a wide range of tasks, such as navigation and locomotion. However, achieving agile control, which pushes the limits of robotic performance, still relies on specialist models that require extensive parameter tuning. To leverage generalist-model adaptability and flexibility while achieving specialist-level agility, we propose AnyCar, a transformer-based generalist dynamics model designed for agile control of various wheeled robots. To collect training data, we unify multiple simulators and leverage different physics backends to simulate vehicles with diverse sizes, scales, and physical properties across various terrains. With robust training and real-world fine-tuning, our model enables precise adaptation to different vehicles, even in the wild and under large state estimation errors. In real-world experiments, AnyCar shows both few-shot and zero-shot generalization across a wide range of vehicles and environments, where our model, combined with a sampling-based MPC, outperforms specialist models by up to 54%. These results represent a key step toward building a foundation model for agile wheeled robot control. We will also open-source our framework to support further research.

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. The One RING: a Robotic Indoor Navigation Generalist

    cs.RO 2024-12 conditional novelty 7.0 of 10

    A simulation-trained policy that randomizes robot body and camera configurations generalizes zero-shot to real robots it has never seen.

  2. Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains

    cs.RO 2026-07 conditional novelty 6.0 of 10

    History-conditioned fine-tuning with targeted synthetic rollouts from a per-terrain bicycle model roughly halves 6 m/s trajectory tracking error against a fine-tuned AnyCar baseline.

  3. Beyond Constant Parameters: Hyper Prediction Models and HyperMPC

    cs.RO 2025-08 unverdicted novelty 6.0 of 10

    A neural network learns how a dynamics model's parameters should evolve over time, letting model predictive control anticipate unmodeled effects and reduce long-horizon prediction errors.

  4. Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics

    cs.RO 2025-02 conditional novelty 6.0 of 10

    Wheeled Lab is an open-source ecosystem that trains three zero-shot RL policies on low-cost wheeled robots in Isaac Lab and deploys them in the real world.

  5. Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics

    cs.RO 2025-01 conditional novelty 6.0 of 10

    A legged-robot controller that estimates payload and friction online and uses those estimates to switch between agile and recovery policies achieves lower collision rates and higher speeds than non-adaptive baselines.

  6. R-CARLA: High-Fidelity Sensor Simulations with Interchangeable Dynamics for Autonomous Racing

    cs.RO 2025-06 reject novelty 5.0 of 10

    R-CARLA integrates custom vehicle dynamics, opponents, and digital-twin maps into CARLA, reporting reduced sim-to-real gaps for racing stacks, but its sensor-simulation improvement is not measured against real sensor data.

  7. YOPO-Rally: A Sim-to-Real Single-Stage Planner for Off-Road Terrain

    cs.RO 2025-05 conditional novelty 5.0 of 10

    A single neural network, YOPO-Rally, plans off-road forest driving from a depth camera after training only in a custom Unity simulator, and is deployed zero-shot on a real robot.

  8. ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills

    cs.RO 2025-02 conditional novelty 5.0 of 10

    ASAP trains a residual action model on real-world rollouts and fine-tunes simulation policies through it, reducing humanoid whole-body motion tracking error in sim-to-real transfer.

Pith tools