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
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.
Forward citations
Cited by 8 Pith papers
-
The One RING: a Robotic Indoor Navigation Generalist
A simulation-trained policy that randomizes robot body and camera configurations generalizes zero-shot to real robots it has never seen.
-
Adapting Generalist Vehicle Models for High-Speed MPC Across Terrains
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.
-
Beyond Constant Parameters: Hyper Prediction Models and HyperMPC
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.
-
Wheeled Lab: Modern Sim2Real for Low-cost, Open-source Wheeled Robotics
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.
-
Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics
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.
-
R-CARLA: High-Fidelity Sensor Simulations with Interchangeable Dynamics for Autonomous Racing
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.
-
YOPO-Rally: A Sim-to-Real Single-Stage Planner for Off-Road Terrain
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.
-
ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
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.
Discussion (0). Continue with ORCID to comment.