Agile Mobility with Rapid Online Adaptation via Meta-learning and Uncertainty-aware MPPI

Modern non-linear model-based controllers require an accurate physics model and model parameters to be able to control mobile robots at their limits. Also, due to surface slipping at high speeds, the friction parameters may continually change (like tire degradation in autonomous racing), and the controller may need to adapt rapidly. Many works derive a task-specific robot model with a parameter adaptation scheme that works well for the task but requires a lot of effort and tuning for each platform and task. In this work, we design a full model-learning-based controller based on meta pre-training that can very quickly adapt using few-shot dynamics data to any wheel-based robot with any model parameters, while also reasoning about model uncertainty. We demonstrate our results in small-scale numeric simulation, the large-scale Unity simulator, and on a medium-scale hardware platform with a wide range of settings. We show that our results are comparable to domain-specific well-engineered controllers, and have excellent generalization performance across all scenarios.

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

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.

Linear Delta Arrays for Dexterous Distributed Manipulation

This paper presents a new type of distributed dexterous manipulators: delta arrays. Each delta array consists of a grid of linearly-actuated delta robots with compliant 3D-printed parallelogram links. These arrays can be used to perform planar transportation tasks, similar to smart conveyors. However, the deltas' additional degrees of freedom also afford a wide range of out-of-plane manipulations, as well as prehensile manipulations between sets of deltas. A delta array thus affords a wide range of distributed manipulation strategies. In this paper, we present the design of the delta arrays, including the individual deltas, a modular array structure, and distributed communication and control. We also construct and evaluate an 8x8 array using the proposed design. Our evaluations show that the resulting 192 DoF robot is capable of performing various coordinated distributed manipulations of a variety of objects, including translation, alignment, and prehensile squeezing.