A runtime assurance system (RTA) for a given plant enables the exercise of an untrusted or experimental controller while assuring safety with a backup (or safety) controller. The relevant computational design problem is to create a logic that assures safety by switching to the safety controller as needed, while maximizing some performance criteria, such as the utilization of the untrusted controller. Existing RTA design strategies are well-known to be overly conservative and, in principle, can lead to safety violations. In this paper, we formulate the optimal RTA design problem and present a new approach for solving it. Our approach relies on reward shaping and reinforcement learning. It can guarantee safety and leverage machine learning technologies for scalability. We have implemented this algorithm and present experimental results comparing our approach with state-of-the-art reachability and simulation-based RTA approaches in a number of scenarios using aircraft models in 3D space with complex safety requirements. Our approach can guarantee safety while increasing utilization of the experimental controller over existing approaches.

The intelligent driver model (IDM) is one of the most widely used car-following (CF) models in recent years. The parameters of this model have been calibrated using real trajectories obtained from naturalistic driving ,driving simulator experiment and drone data. An important aspect of the model calibration process is defining the main objective of the calibration. This objective, influences the objective function and the performance measure for the calibration. For example, to calibrate CF models, the objective is usually to minimize the error in measured spacing or speed while important safety aspects of the models such as the collision avoidance mechanisms are ignored. For such models, there is no guarantee that the calibrated parameters will preserve the safety properties of the model since they are not explicitly taken into account. To explicitly account for the safety properties during calibration, this paper proposes a simple objective function which minimizes both the error in the actual measured spacing (as it is currently done) and the error in the dynamic safety spacing (desired minimum gap) derived from the collision free property of the IDM model. The proposed objective function is used to calibrate two variants of the IDM using vehicle trajectories obtained with drone from a Dutch highway. The calibration performance is then compared in terms of the error in actual spacing and time gap. The results show that the proposed safety objective 15 function leads to lower errors in spacing and time gap compared to when minimizing for only spacing and preserves collision property of the IDM.

The Close Enough Traveling Salesman Problem (CETSP) is a well-known variant of the classic Traveling Salesman Problem whereby the agent may complete its mission at any point within a target neighborhood. Heuristics based on overlapped neighborhoods, known as Steiner Zones (SZ), have gained attention in addressing CETSPs. While SZs offer effective approximations to the original graph, their inherent overlap imposes constraints on the search space, potentially conflicting with global optimization objectives. Here we present the Close Enough Orienteering Problem with Non-uniform Neighborhoods (CEOP-N), which extends CETSP by introducing variable prize attributes and non-uniform cost considerations for prize collection. To tackle CEOP-N, we develop a new approach featuring a Randomized Steiner Zone Discretization (RSZD) scheme coupled with a hybrid algorithm based on Particle Swarm Optimization (PSO) and Ant Colony System (ACS) - CRaSZe-AntS. The RSZD scheme identifies sub-regions for PSO exploration, and ACS determines the discrete visiting sequence. We evaluate the RSZD's discretization performance on CEOP instances derived from established CETSP instances, and compare CRaSZe-AntS against the most relevant state-of-the-art heuristic focused on single-neighborhood optimization for CEOP. We also compare the performance of the interior search within SZs and the boundary search on individual neighborhoods in the context of CEOP-N. Our results show CRaSZe-AntS can yield comparable solution quality with significantly reduced computation time compared to the single-neighborhood strategy, where we observe an averaged 140.44% increase in prize collection and 55.18% reduction of execution time. CRaSZe-AntS is thus highly effective in solving emerging CEOP-N, examples of which include truck-and-drone delivery scenarios.

We assess the fidelity of our dataset by investigating the cross-view vertex distance and the 3D motion stability index. We demonstrate that our dataset contains more spatio-temporally consistent and accurate 3D meshes than the competing datasets built with strong baseline methods. To demonstrate the potential of our dataset, we present two applications: (1) improving the accuracy of a face reconstruction model and (2) learning a generative 3D facial motion prior. These applications highlight that NeuFace-dataset can be further used in diverse applications demanding high-quality and large-scale 3D face meshes. We summarize our main contributions as follows: NeuFace, an optimization method for reconstructing accurate and spatio-temporally consistent 3D face meshes on videos via neural re-parameterization. NeuFace-dataset, the first large-scale 3D face mesh pseudo-labels constructed by curating existing large-scale 2D face video datasets with our method. Demonstrating the benefits of NeuFace-dataset: (1) improve the accuracy of off-the-shelf face mesh regressors, (2) learn 3D facial motion prior for long-term face motion generation.

Federated learning (FL) is a distributed machine learning framework where the global model of a central server is trained via multiple collaborative steps by participating clients without sharing their data. While being a flexible framework, where the distribution of local data, participation rate, and computing power of each client can greatly vary, such flexibility gives rise to many new challenges, especially in the hyperparameter tuning on the client side. We propose $\Delta$-SGD, a simple step size rule for SGD that enables each client to use its own step size by adapting to the local smoothness of the function each client is optimizing. We provide theoretical and empirical results where the benefit of the client adaptivity is shown in various FL scenarios.

With the aim of further enabling the exploitation of intentional impacts in robotic manipulation, a control framework is presented that directly tackles the challenges posed by tracking control of robotic manipulators that are tasked to perform nominally simultaneous impacts. This framework is an extension of the reference spreading control framework, in which overlapping ante- and post-impact references that are consistent with impact dynamics are defined. In this work, such a reference is constructed starting from a teleoperation-based approach. By using the corresponding ante- and post-impact control modes in the scope of a quadratic programming control approach, peaking of the velocity error and control inputs due to impacts is avoided while maintaining high tracking performance. With the inclusion of a novel interim mode, we aim to also avoid input peaks and steps when uncertainty in the environment causes a series of unplanned single impacts to occur rather than the planned simultaneous impact. This work in particular presents for the first time an experimental evaluation of reference spreading control on a robotic setup, showcasing its robustness against uncertainty in the environment compared to three baseline control approaches.

Nowadays, state-of-the-art learning-to-rank methods are based on gradient-boosted decision trees (GBDT). The most well-known algorithm is LambdaMART which was proposed more than a decade ago. Recently, several other GBDT-based ranking algorithms were proposed. In this paper, we thoroughly analyze these methods in a unified setup. In particular, we address the following questions. Is direct optimization of a smoothed ranking loss preferable over optimizing a convex surrogate? How to properly construct and smooth surrogate ranking losses? To address these questions, we compare LambdaMART with YetiRank and StochasticRank methods and their modifications. We also propose a simple improvement of the YetiRank approach that allows for optimizing specific ranking loss functions. As a result, we gain insights into learning-to-rank techniques and obtain a new state-of-the-art algorithm.

We propose a motion planner for cable-driven payload transportation using multiple unmanned aerial vehicles (UAVs) in an environment cluttered with obstacles. Our planner is kinodynamic, i.e., it considers the full dynamics model of the transporting system including actuation constraints. Due to the high dimensionality of the planning problem, we use a hierarchical approach where we first solve the geometric motion planning using a sampling-based method with a novel sampler, followed by constrained trajectory optimization that considers the full dynamics of the system. Both planning stages consider inter-robot and robot/obstacle collisions. We demonstrate in a software-in-the-loop simulation that there is a significant benefit in kinodynamic motion planning for such payload transport systems with respect to payload tracking error and energy consumption compared to the standard methods of planning for the payload alone. Notably, we observe a significantly higher success rate in scenarios where the team formation changes are needed to move through tight spaces.

Basis splines enable a time-continuous feasibility check with a finite number of constraints. Constraints apply to the whole trajectory for motion planning applications that require a collision-free and dynamically feasible trajectory. Existing motion planners that rely on gradient-based optimization apply time scaling to implement a shrinking planning horizon. They neither guarantee a recursively feasible trajectory nor enable reaching two terminal manifold parts at different time scales. This paper proposes a nonlinear optimization problem that addresses the drawbacks of existing approaches. Therefore, the spline breakpoints are included in the optimization variables. Transformations between spline bases are implemented so a sparse problem formulation is achieved. A strategy for breakpoint removal enables the convergence into a terminal manifold. The evaluation in an overtaking scenario shows the influence of the breakpoint number on the solution quality and the time required for optimization.

Bilevel optimization has recently regained interest owing to its applications in emerging machine learning fields such as hyperparameter optimization, meta-learning, and reinforcement learning. Recent results have shown that simple alternating (implicit) gradient-based algorithms can match the convergence rate of single-level gradient descent (GD) when addressing bilevel problems with a strongly convex lower-level objective. However, it remains unclear whether this result can be generalized to bilevel problems beyond this basic setting. In this paper, we first introduce a stationary metric for the considered bilevel problems, which generalizes the existing metric, for a nonconvex lower-level objective that satisfies the Polyak-{\L}ojasiewicz (PL) condition. We then propose a Generalized ALternating mEthod for bilevel opTimization (GALET) tailored to BLO with convex PL LL problem and establish that GALET achieves an $\epsilon$-stationary point for the considered problem within $\tilde{\cal O}(\epsilon^{-1})$ iterations, which matches the iteration complexity of GD for single-level smooth nonconvex problems.