Knut Åkesson

Zahra Ramezani, Kenan Šehić, Luigi Nardi et al.

Cyber-physical systems (CPSs) are often complex and safety-critical, making it both challenging and crucial to ensure that the system's specifications are met. Simulation-based falsification is a practical testing technique for increasing confidence in a CPS's correctness, as it only requires that the system be simulated. Reducing the number of computationally intensive simulations needed for falsification is a key concern. In this study, we investigate Bayesian optimization (BO), a sample-efficient approach that learns a surrogate model to capture the relationship between input signal parameterization and specification evaluation. We propose two enhancements to the basic BO for improving falsification: (1) leveraging local surrogate models, and (2) utilizing the user's prior knowledge. Additionally, we address the formulation of acquisition functions for falsification by proposing and evaluating various alternatives. Our benchmark evaluation demonstrates significant improvements when using local surrogate models in BO for falsifying challenging benchmark examples. Incorporating prior knowledge is found to be especially beneficial when the simulation budget is constrained. For some benchmark problems, the choice of acquisition function noticeably impacts the number of simulations required for successful falsification.

Erik Brorsson, Knut Åkesson, Lennart Svensson et al.

We consider unsupervised domain adaptation (UDA) for semantic segmentation in which the model is trained on a labeled source dataset and adapted to an unlabeled target dataset. Unfortunately, current self-training methods are susceptible to misclassified pseudo-labels resulting from erroneous predictions. Since certain classes are typically associated with less reliable predictions in UDA, reducing the impact of such pseudo-labels without skewing the training towards some classes is notoriously difficult. To this end, we propose an extensive cut-and-paste strategy (ECAP) to leverage reliable pseudo-labels through data augmentation. Specifically, ECAP maintains a memory bank of pseudo-labeled target samples throughout training and cut-and-pastes the most confident ones onto the current training batch. We implement ECAP on top of the recent method MIC and boost its performance on two synthetic-to-real domain adaptation benchmarks. Notably, MIC+ECAP reaches an unprecedented performance of 69.1 mIoU on the Synthia->Cityscapes benchmark. Our code is available at https://github.com/ErikBrorsson/ECAP.

Lasse Kötz, Knut Åkesson

Falsification of hybrid dynamical systems remains challenging due to mode-dependent dynamics and discrete transitions. In this work, we propose a surrogate-based falsification approach that enables hybrid systems by learning a differentiable hybrid automaton model from data. This extends previous surrogate-based falsification methods, which were limited to purely continuous dynamics. Specifically, we employ neural hybrid automata to learn both a latent mode encoder and the corresponding mode-conditioned vector fields. Once the surrogate has paired each mode with an associated vector field, the transition guards are inferred using existing trajectory data. The learned surrogate is subsequently subjected to a gradient-based optimal control formulation, which minimizes a smooth approximation of the safety specification to find safety violations. In the last step, an experiment with the optimal control solution is carried out on the original system to ensure soundness. The proposed method consistently uncovers counterexamples on a majority of evaluated benchmark specifications; on these cases, it achieves competitive or improved sample efficiency than other tools while using a reduced simulation budget.

Kilian Freitag, Kristian Ceder, Rita Laezza et al.

Reinforcement learning (RL) has emerged as a powerful tool for tackling control problems, but its practical application is often hindered by the complexity arising from intricate reward functions with multiple terms. The reward hypothesis posits that any objective can be encapsulated in a scalar reward function, yet balancing individual, potentially adversarial, reward terms without exploitation remains challenging. To overcome the limitations of traditional RL methods, which often require precise balancing of competing reward terms, we propose a two-stage reward curriculum that first maximizes a simple reward function and then transitions to the full, complex reward. We provide a method based on how well an actor fits a critic to automatically determine the transition point between the two stages. Additionally, we introduce a flexible replay buffer that enables efficient phase transfer by reusing samples from one stage in the next. We evaluate our method on the DeepMind control suite, modified to include an additional constraint term in the reward definitions. We further evaluate our method in a mobile robot scenario with even more competing reward terms. In both settings, our two-stage reward curriculum achieves a substantial improvement in performance compared to a baseline trained without curriculum. Instead of exploiting the constraint term in the reward, it is able to learn policies that balance task completion and constraint satisfaction. Our results demonstrate the potential of two-stage reward curricula for efficient and stable RL in environments with complex rewards, paving the way for more robust and adaptable robotic systems in real-world applications.

Ze Zhang, Georg Hess, Junjie Hu et al.

This paper proposes an integrated approach for the safe and efficient control of mobile robots in dynamic and uncertain environments. The approach consists of two key steps: one-shot multimodal motion prediction to anticipate motions of dynamic obstacles and model predictive control to incorporate these predictions into the motion planning process. Motion prediction is driven by an energy-based neural network that generates high-resolution, multi-step predictions in a single operation. The prediction outcomes are further utilized to create geometric shapes formulated as mathematical constraints. Instead of treating each dynamic obstacle individually, predicted obstacles are grouped by proximity in an unsupervised way to improve performance and efficiency. The overall collision-free navigation is handled by model predictive control with a specific design for proactive dynamic obstacle avoidance. The proposed approach allows mobile robots to navigate effectively in dynamic environments. Its performance is accessed across various scenarios that represent typical warehouse settings. The results demonstrate that the proposed approach outperforms other existing dynamic obstacle avoidance methods.

Erik Brorsson, Lennart Svensson, Kristofer Bengtsson et al.

We address multi-view pedestrian detection in a setting where labeled data is collected using a multi-camera setup different from the one used for testing. While recent multi-view pedestrian detectors perform well on the camera rig used for training, their performance declines when applied to a different setup. To facilitate seamless deployment across varied camera rigs, we propose an unsupervised domain adaptation (UDA) method that adapts the model to new rigs without requiring additional labeled data. Specifically, we leverage the mean teacher self-training framework with a novel pseudo-labeling technique tailored to multi-view pedestrian detection. This method achieves state-of-the-art performance on multiple benchmarks, including MultiviewX$\rightarrow$Wildtrack. Unlike previous methods, our approach eliminates the need for external labeled monocular datasets, thereby reducing reliance on labeled data. Extensive evaluations demonstrate the effectiveness of our method and validate key design choices. By enabling robust adaptation across camera setups, our work enhances the practicality of multi-view pedestrian detectors and establishes a strong UDA baseline for future research.

Kilian Freitag, Knut Åkesson, Morteza Haghir Chehreghani

Deep Reinforcement Learning is a promising tool for robotic control, yet practical application is often hindered by the difficulty of designing effective reward functions. Real-world tasks typically require optimizing multiple objectives simultaneously, necessitating precise tuning of their weights to learn a policy with the desired characteristics. To address this, we propose a two-stage reward curriculum where we decouple task-specific objectives from behavioral terms. In our method, we first train the agent on a simplified task-only reward function to ensure effective exploration before introducing the full reward that includes auxiliary behavior-related terms such as energy efficiency. Further, we analyze various transition strategies and demonstrate that reusing samples between phases is critical for training stability. We validate our approach on the DeepMind Control Suite, ManiSkill3, and a mobile robot environment, modified to include auxiliary behavioral objectives. Our method proves to be simple yet effective, substantially outperforming baselines trained directly on the full reward while exhibiting higher robustness to specific reward weightings.

Sabino Francesco Roselli, Martin Fabian, Knut Åkesson

The Vehicle Routing Problem (VRP) is the combinatorial optimization problem of designing routes for vehicles to visit customers in such a fashion that a cost function, typically the number of vehicles, or the total travelled distance is minimized. The problem finds applications in industrial scenarios, for example where Automated Guided Vehicles run through the plant to deliver components from the warehouse. This specific problem, henceforth called the Electric Conflict-Free Vehicle Routing Problem (CF-EVRP), involves constraints such as limited operating range of the vehicles, time windows on the delivery to the customers, and limited capacity on the number of vehicles the road segments can accommodate at the same time. Such a complex system results in a large model that cannot easily be solved to optimality in reasonable time. We therefore developed a compositional model that breaks down the problem into smaller and simpler sub-problems and provides sub-optimal, feasible solutions to the original problem. The algorithm exploits the strengths of SMT solvers, which proved in our previous work to be an efficient approach to deal with scheduling problems. Compared to a monolithic model for the CF-EVRP, written in the SMT standard language and solved using a state-of-the-art SMT solver the compositional model was found to be significantly faster.