Diffusion models have recently gained popularity for policy learning in robotics due to their ability to capture high-dimensional and multimodal distributions. However, diffusion policies are inherently stochastic and typically trained offline, limiting their ability to handle unseen and dynamic conditions where novel constraints not represented in the training data must be satisfied. To overcome this limitation, we propose diffusion predictive control with constraints (DPCC), an algorithm for diffusion-based control with explicit state and action constraints that can deviate from those in the training data. DPCC uses constraint tightening and incorporates model-based projections into the denoising process of a trained trajectory diffusion model. This allows us to generate constraint-satisfying, dynamically feasible, and goal-reaching trajectories for predictive control. We show through simulations of a robot manipulator that DPCC outperforms existing methods in satisfying novel test-time constraints while maintaining performance on the learned control task.

Controller tuning is crucial for closed-loop performance but often involves manual adjustments. Although Bayesian optimization (BO) has been established as a data-efficient method for automated tuning, applying it to large and high-dimensional search spaces remains challenging. We extend a recently proposed local variant of BO to include crash constraints, where the controller can only be successfully evaluated in an a-priori unknown feasible region. We demonstrate the efficiency of the proposed method through simulations and hardware experiments. Our findings showcase the potential of local BO to enhance controller performance and reduce the time and resources necessary for tuning.

How can robots learn and adapt to new tasks and situations with little data? Systematic exploration and simulation are crucial tools for efficient robot learning. We present a novel black-box policy search algorithm focused on data-efficient policy improvements. The algorithm learns directly on the robot and treats simulation as an additional information source to speed up the learning process. At the core of the algorithm, a probabilistic model learns the dependence of the policy parameters and the robot learning objective not only by performing experiments on the robot, but also by leveraging data from a simulator. This substantially reduces interaction time with the robot. Using this model, we can guarantee improvements with high probability for each policy update, thereby facilitating fast, goal-oriented learning. We evaluate our algorithm on simulated fine-tuning tasks and demonstrate the data-efficiency of the proposed dual-information source optimization algorithm. In a real robot learning experiment, we show fast and successful task learning on a robot manipulator with the aid of an imperfect simulator.

Deep Reinforcement Learning (DRL) in simulation often results in brittle and unrealistic learning outcomes. To push the agent towards more desirable solutions, prior information can be injected in the learning process through, for instance, reward shaping, expert data, or motion primitives. We propose an additional inductive bias for robot learning: latent actions learned from expert demonstration as priors in the action space. We show that these action priors can be learned from only a single open-loop gait cycle using a simple autoencoder. Using these latent action priors combined with established style rewards for imitation in DRL achieves above expert demonstration level of performance and leads to more desirable gaits. Further, action priors substantially improve the performance on transfer tasks, even leading to gait transitions for higher target speeds. Videos and code are available at https://sites.google.com/view/latent-action-priors.

We consider the problem of sequentially optimizing a time-varying objective function using time-varying Bayesian optimization (TVBO). To cope with stale data arising from time variations, current approaches to TVBO require prior knowledge of a constant rate of change. However, in practice, the rate of change is usually unknown. We propose an event-triggered algorithm, ET-GP-UCB, that treats the optimization problem as static until it detects changes in the objective function online and then resets the dataset. This allows the algorithm to adapt to realized temporal changes without the need for prior knowledge. The event-trigger is based on probabilistic uniform error bounds used in Gaussian process regression. We show in numerical experiments that ET-GP-UCB outperforms state-of-the-art algorithms on synthetic and real-world data and provide regret bounds for the proposed algorithm. The results demonstrate that ET-GP-UCB is readily applicable without prior knowledge on the rate of change.

Learning-based control uses data to design efficient controllers for specific systems. When multiple systems are involved, experience transfer usually focuses on data availability and controller performance yet neglects robustness to variations between systems. In contrast, this letter explores experience transfer from a robustness perspective. We leverage the transfer to design controllers that are robust not only to the uncertainty regarding an individual agent's model but also to the choice of agent in a fleet. Experience transfer enables the design of safe and robust controllers that work out of the box for all systems in a heterogeneous fleet. Our approach combines scenario optimization and recent formulations for direct data-driven control without the need to estimate a model of the system or determine uncertainty bounds for its parameters. We demonstrate the benefits of our data-driven robustification method through a numerical case study and obtain learned controllers that generalize well from a small number of open-loop trajectories in a quadcopter simulation.

Automated bin-picking is a prerequisite for fully automated manufacturing and warehouses. To successfully pick an item from an unstructured bin the robot needs to first detect possible grasps for the objects, decide on the object to remove and consequently plan and execute a feasible trajectory to retrieve the chosen object. Over the last years significant progress has been made towards solving these problems. However, when multiple robot arms are cooperating the decision and planning problems become exponentially harder. We propose an integrated multi-arm bin-picking pipeline (IMAPIP), and demonstrate that it is able to reliably pick objects from a bin in real-time using multiple robot arms. IMAPIP solves the multi-arm bin-picking task first at high-level using a geometry-aware policy integrated in a combined task and motion planning framework. We then plan motions consistent with this policy using the BIT* algorithm on the motion planning level. We show that this integrated solution enables robot arm cooperation. In our experiments, we show the proposed geometry-aware policy outperforms a baseline by increasing bin-picking time by 28\% using two robot arms. The policy is robust to changes in the position of the bin and number of objects. We also show that IMAPIP to successfully scale up to four robot arms working in close proximity.

Robust controllers ensure stability in feedback loops designed under uncertainty but at the cost of performance. Model uncertainty in time-invariant systems can be reduced by recently proposed learning-based methods, which improve the performance of robust controllers using data. However, in practice, many systems also exhibit uncertainty in the form of changes over time, e.g., due to weight shifts or wear and tear, leading to decreased performance or instability of the learning-based controller. We propose an event-triggered learning algorithm that decides when to learn in the face of uncertainty in the LQR problem with rare or slow changes. Our key idea is to switch between robust and learned controllers. For learning, we first approximate the optimal length of the learning phase via Monte-Carlo estimations using a probabilistic model. We then design a statistical test for uncertain systems based on the moment-generating function of the LQR cost. The test detects changes in the system under control and triggers re-learning when control performance deteriorates due to system changes. We demonstrate improved performance over a robust controller baseline in a numerical example.

Changing conditions or environments can cause system dynamics to vary over time. To ensure optimal control performance, controllers should adapt to these changes. When the underlying cause and time of change is unknown, we need to rely on online data for this adaptation. In this paper, we will use time-varying Bayesian optimization (TVBO) to tune controllers online in changing environments using appropriate prior knowledge on the control objective and its changes. Two properties are characteristic of many online controller tuning problems: First, they exhibit incremental and lasting changes in the objective due to changes to the system dynamics, e.g., through wear and tear. Second, the optimization problem is convex in the tuning parameters. Current TVBO methods do not explicitly account for these properties, resulting in poor tuning performance and many unstable controllers through over-exploration of the parameter space. We propose a novel TVBO forgetting strategy using Uncertainty-Injection (UI), which incorporates the assumption of incremental and lasting changes. The control objective is modeled as a spatio-temporal Gaussian process (GP) with UI through a Wiener process in the temporal domain. Further, we explicitly model the convexity assumptions in the spatial dimension through GP models with linear inequality constraints. In numerical experiments, we show that our model outperforms the state-of-the-art method in TVBO, exhibiting reduced regret and fewer unstable parameter configurations.

Reinforcement learning (RL) aims to find an optimal policy by interaction with an environment. Consequently, learning complex behavior requires a vast number of samples, which can be prohibitive in practice. Nevertheless, instead of systematically reasoning and actively choosing informative samples, policy gradients for local search are often obtained from random perturbations. These random samples yield high variance estimates and hence are sub-optimal in terms of sample complexity. Actively selecting informative samples is at the core of Bayesian optimization, which constructs a probabilistic surrogate of the objective from past samples to reason about informative subsequent ones. In this paper, we propose to join both worlds. We develop an algorithm utilizing a probabilistic model of the objective function and its gradient. Based on the model, the algorithm decides where to query a noisy zeroth-order oracle to improve the gradient estimates. The resulting algorithm is a novel type of policy search method, which we compare to existing black-box algorithms. The comparison reveals improved sample complexity and reduced variance in extensive empirical evaluations on synthetic objectives. Further, we highlight the benefits of active sampling on popular RL benchmarks.