The Mini Wheelbot Dataset: High-Fidelity Data for Robot Learning

The development of robust learning-based control algorithms for unstable systems requires high-quality, real-world data, yet access to specialized robotic hardware remains a significant barrier for many researchers. This paper introduces a comprehensive dynamics dataset for the Mini Wheelbot, an open-source, quasi-symmetric balancing reaction wheel unicycle. The dataset provides 1 kHz synchronized data encompassing all onboard sensor readings, state estimates, ground-truth poses from a motion capture system, and third-person video logs. To ensure data diversity, we include experiments across multiple hardware instances and surfaces using various control paradigms, including pseudo-random binary excitation, nonlinear model predictive control, and reinforcement learning agents. We include several example applications in dynamics model learning, state estimation, and time-series classification to illustrate common robotics algorithms that can be benchmarked on our dataset.

Fine-Tuning of Neural Network Approximate MPC without Retraining via Bayesian Optimization

Approximate model-predictive control (AMPC) aims to imitate an MPC's behavior with a neural network, removing the need to solve an expensive optimization problem at runtime. However, during deployment, the parameters of the underlying MPC must usually be fine-tuned. This often renders AMPC impractical as it requires repeatedly generating a new dataset and retraining the neural network. Recent work addresses this problem by adapting AMPC without retraining using approximated sensitivities of the MPC's optimization problem. Currently, this adaption must be done by hand, which is labor-intensive and can be unintuitive for high-dimensional systems. To solve this issue, we propose using Bayesian optimization to tune the parameters of AMPC policies based on experimental data. By combining model-based control with direct and local learning, our approach achieves superior performance to nominal AMPC on hardware, with minimal experimentation. This allows automatic and data-efficient adaptation of AMPC to new system instances and fine-tuning to cost functions that are difficult to directly implement in MPC. We demonstrate the proposed method in hardware experiments for the swing-up maneuver on an inverted cartpole and yaw control of an under-actuated balancing unicycle robot, a challenging control problem.

A Systems-Theoretic View on the Convergence of Algorithms under Disturbances

Algorithms increasingly operate within complex physical, social, and engineering systems where they are exposed to disturbances, noise, and interconnections with other dynamical systems. This article extends known convergence guarantees of an algorithm operating in isolation (i.e., without disturbances) and systematically derives stability bounds and convergence rates in the presence of such disturbances. By leveraging converse Lyapunov theorems, we derive key inequalities that quantify the impact of disturbances. We further demonstrate how our result can be utilized to assess the effects of disturbances on algorithmic performance in a wide variety of applications, including communication constraints in distributed learning, sensitivity in machine learning generalization, and intentional noise injection for privacy. This underpins the role of our result as a unifying tool for algorithm analysis in the presence of noise, disturbances, and interconnections with other dynamical systems.

Sailing Towards Zero-Shot State Estimation using Foundation Models Combined with a UKF

State estimation in control and systems engineering traditionally requires extensive manual system identification or data-collection effort. However, transformer-based foundation models in other domains have reduced data requirements by leveraging pre-trained generalist models. Ultimately, developing zero-shot foundation models of system dynamics could drastically reduce manual deployment effort. While recent work shows that transformer-based end-to-end approaches can achieve zero-shot performance on unseen systems, they are limited to sensor models seen during training. We introduce the foundation model unscented Kalman filter (FM-UKF), which combines a transformer-based model of system dynamics with analytically known sensor models via an UKF, enabling generalization across varying dynamics without retraining for new sensor configurations. We evaluate FM-UKF on a new benchmark of container ship models with complex dynamics, demonstrating a competitive accuracy, effort, and robustness trade-off compared to classical methods with approximate system knowledge and to an end-to-end approach. The benchmark and dataset are open sourced to further support future research in zero-shot state estimation via foundation models.

Viability of Future Actions: Robust Safety in Reinforcement Learning via Entropy Regularization

Despite the many recent advances in reinforcement learning (RL), the question of learning policies that robustly satisfy state constraints under unknown disturbances remains open. In this paper, we offer a new perspective on achieving robust safety by analyzing the interplay between two well-established techniques in model-free RL: entropy regularization, and constraints penalization. We reveal empirically that entropy regularization in constrained RL inherently biases learning toward maximizing the number of future viable actions, thereby promoting constraints satisfaction robust to action noise. Furthermore, we show that by relaxing strict safety constraints through penalties, the constrained RL problem can be approximated arbitrarily closely by an unconstrained one and thus solved using standard model-free RL. This reformulation preserves both safety and optimality while empirically improving resilience to disturbances. Our results indicate that the connection between entropy regularization and robustness is a promising avenue for further empirical and theoretical investigation, as it enables robust safety in RL through simple reward shaping.

A kernel conditional two-sample test

We propose a framework for hypothesis testing on conditional probability distributions, which we then use to construct conditional two-sample statistical tests. These tests identify the inputs -- called covariates in this context -- where two conditional expectations differ with high probability. Our key idea is to transform confidence bounds of a learning method into a conditional two-sample test, and we instantiate this principle for kernel ridge regression (KRR) and conditional kernel mean embeddings. We generalize existing pointwise-in-time or time-uniform confidence bounds for KRR to previously-inaccessible yet essential cases such as infinite-dimensional outputs with non-trace-class kernels. These bounds enable circumventing the need for independent data in our statistical tests, since they allow online sampling. We also introduce bootstrapping schemes leveraging the parametric form of testing thresholds identified in theory to avoid tuning inaccessible parameters, making our method readily applicable in practice. Such conditional two-sample tests are especially relevant in applications where data arrive sequentially or non-independently, or when output distributions vary with operational parameters. We demonstrate their utility through examples in process monitoring and comparison of dynamical systems. Overall, our results establish a comprehensive foundation for conditional two-sample testing, from theoretical guarantees to practical implementation, and advance the state-of-the-art on the concentration of vector-valued least squares estimation.

Concept Extraction for Time Series with ECLAD-ts

Convolutional neural networks (CNNs) for time series classification (TSC) are being increasingly used in applications ranging from quality prediction to medical diagnosis. The black box nature of these models makes understanding their prediction process difficult. This issue is crucial because CNNs are prone to learning shortcuts and biases, compromising their robustness and alignment with human expectations. To assess whether such mechanisms are being used and the associated risk, it is essential to provide model explanations that reflect the inner workings of the model. Concept Extraction (CE) methods offer such explanations, but have mostly been developed for the image domain so far, leaving a gap in the time series domain. In this work, we present a CE and localization method tailored to the time series domain, based on the ideas of CE methods for images. We propose the novel method ECLAD-ts, which provides post-hoc global explanations based on how the models encode subsets of the input at different levels of abstraction. For this, concepts are produced by clustering timestep-wise aggregations of CNN activation maps, and their importance is computed based on their impact on the prediction process. We evaluate our method on synthetic and natural datasets. Furthermore, we assess the advantages and limitations of CE in time series through empirical results. Our results show that ECLAD-ts effectively explains models by leveraging their internal representations, providing useful insights about their prediction process.

Diffusion-Based Approximate MPC: Fast and Consistent Imitation of Multi-Modal Action Distributions

Approximating model predictive control (MPC) using imitation learning (IL) allows for fast control without solving expensive optimization problems online. However, methods that use neural networks in a simple L2-regression setup fail to approximate multi-modal (set-valued) solution distributions caused by local optima found by the numerical solver or non-convex constraints, such as obstacles, significantly limiting the applicability of approximate MPC in practice. We solve this issue by using diffusion models to accurately represent the complete solution distribution (i.e., all modes) at high control rates (more than 1000 Hz). This work shows that diffusion based AMPC significantly outperforms L2-regression-based approximate MPC for multi-modal action distributions. In contrast to most earlier work on IL, we also focus on running the diffusion-based controller at a higher rate and in joint space instead of end-effector space. Additionally, we propose the use of gradient guidance during the denoising process to consistently pick the same mode in closed loop to prevent switching between solutions. We propose using the cost and constraint satisfaction of the original MPC problem during parallel sampling of solutions from the diffusion model to pick a better mode online. We evaluate our method on the fast and accurate control of a 7-DoF robot manipulator both in simulation and on hardware deployed at 250 Hz, achieving a speedup of more than 70 times compared to solving the MPC problem online and also outperforming the numerical optimization (used for training) in success ratio.

The Mini Wheelbot: A Testbed for Learning-based Balancing, Flips, and Articulated Driving

The Mini Wheelbot is a balancing, reaction wheel unicycle robot designed as a testbed for learning-based control. It is an unstable system with highly nonlinear yaw dynamics, non-holonomic driving, and discrete contact switches in a small, powerful, and rugged form factor. The Mini Wheelbot can use its wheels to stand up from any initial orientation - enabling automatic environment resets in repetitive experiments and even challenging half flips. We illustrate the effectiveness of the Mini Wheelbot as a testbed by implementing two popular learning-based control algorithms. First, we showcase Bayesian optimization for tuning the balancing controller. Second, we use imitation learning from an expert nonlinear MPC that uses gyroscopic effects to reorient the robot and can track higher-level velocity and orientation commands. The latter allows the robot to drive around based on user commands - for the first time in this class of robots. The Mini Wheelbot is not only compelling for testing learning-based control algorithms, but it is also just fun to work with, as demonstrated in the video of our experiments.

On Rollouts in Model-Based Reinforcement Learning

Model-based reinforcement learning (MBRL) seeks to enhance data efficiency by learning a model of the environment and generating synthetic rollouts from it. However, accumulated model errors during these rollouts can distort the data distribution, negatively impacting policy learning and hindering long-term planning. Thus, the accumulation of model errors is a key bottleneck in current MBRL methods. We propose Infoprop, a model-based rollout mechanism that separates aleatoric from epistemic model uncertainty and reduces the influence of the latter on the data distribution. Further, Infoprop keeps track of accumulated model errors along a model rollout and provides termination criteria to limit data corruption. We demonstrate the capabilities of Infoprop in the Infoprop-Dyna algorithm, reporting state-of-the-art performance in Dyna-style MBRL on common MuJoCo benchmark tasks while substantially increasing rollout length and data quality.