In this work, the problem of 4 degree-of-freedom (3D position and heading) robot-to-robot relative frame transformation estimation using onboard odometry and inter-robot distance measurements is studied. Firstly, we present a theoretical analysis of the problem, namely the derivation and interpretation of the Cramer-Rao Lower Bound (CRLB), the Fisher Information Matrix (FIM) and its determinant. Secondly, we propose optimization-based methods to solve the problem, including a quadratically constrained quadratic programming (QCQP) and the corresponding semidefinite programming (SDP) relaxation. Moreover, we address practical issues that are ignored in previous works, such as accounting for spatial-temporal offsets between the ultra-wideband (UWB) and odometry sensors, rejecting UWB outliers and checking for singular configurations before commencing operation. Lastly, extensive simulations and real-life experiments with aerial robots show that the proposed QCQP and SDP methods outperform state-of-the-art methods, especially in geometrically poor or large measurement noise conditions. In general, the QCQP method provides the best results at the expense of computational time, while the SDP method runs much faster and is sufficiently accurate in most cases.

We present Bayesian Team Imitation Learner (BTIL), an imitation learning algorithm to model the behavior of teams performing sequential tasks in Markovian domains. In contrast to existing multi-agent imitation learning techniques, BTIL explicitly models and infers the time-varying mental states of team members, thereby enabling learning of decentralized team policies from demonstrations of suboptimal teamwork. Further, to allow for sample- and label-efficient policy learning from small datasets, BTIL employs a Bayesian perspective and is capable of learning from semi-supervised demonstrations. We demonstrate and benchmark the performance of BTIL on synthetic multi-agent tasks as well as a novel dataset of human-agent teamwork. Our experiments show that BTIL can successfully learn team policies from demonstrations despite the influence of team members' (time-varying and potentially misaligned) mental states on their behavior.

Conventional frequentist FL schemes are known to yield overconfident decisions. Bayesian FL addresses this issue by allowing agents to process and exchange uncertainty information encoded in distributions over the model parameters. However, this comes at the cost of a larger per-iteration communication overhead. This letter investigates whether Bayesian FL can still provide advantages in terms of calibration when constraining communication bandwidth. We present compressed particle-based Bayesian FL protocols for FL and federated "unlearning" that apply quantization and sparsification across multiple particles. The experimental results confirm that the benefits of Bayesian FL are robust to bandwidth constraints.

Simulating trajectories of virtual crowds is a commonly encountered task in Computer Graphics. Several recent works have applied Reinforcement Learning methods to animate virtual agents, however they often make different design choices when it comes to the fundamental simulation setup. Each of these choices comes with a reasonable justification for its use, so it is not obvious what is their real impact, and how they affect the results. In this work, we analyze some of these arbitrary choices in terms of their impact on the learning performance, as well as the quality of the resulting simulation measured in terms of the energy efficiency. We perform a theoretical analysis of the properties of the reward function design, and empirically evaluate the impact of using certain observation and action spaces on a variety of scenarios, with the reward function and energy usage as metrics. We show that directly using the neighboring agents' information as observation generally outperforms the more widely used raycasting. Similarly, using nonholonomic controls with egocentric observations tends to produce more efficient behaviors than holonomic controls with absolute observations. Each of these choices has a significant, and potentially nontrivial impact on the results, and so researchers should be mindful about choosing and reporting them in their work.

Recent work in reinforcement learning has focused on several characteristics of learned policies that go beyond maximizing reward. These properties include fairness, explainability, generalization, and robustness. In this paper, we define interventional robustness (IR), a measure of how much variability is introduced into learned policies by incidental aspects of the training procedure, such as the order of training data or the particular exploratory actions taken by agents. A training procedure has high IR when the agents it produces take very similar actions under intervention, despite variation in these incidental aspects of the training procedure. We develop an intuitive, quantitative measure of IR and calculate it for eight algorithms in three Atari environments across dozens of interventions and states. From these experiments, we find that IR varies with the amount of training and type of algorithm and that high performance does not imply high IR, as one might expect.

This paper presents a solution to the automatic task planning problem for multi-agent systems. A formal framework is developed based on the Nondeterministic Finite Automata with $\epsilon$-transitions, where given the capabilities, constraints and failure modes of the agents involved, an initial state of the system and a task specification, an optimal solution is generated that satisfies the system constraints and the task specification. The resulting solution is guaranteed to be complete and optimal; moreover a heuristic solution that offers significant reduction of the computational requirements while relaxing the completeness and optimality requirements is proposed. The constructed system model is independent from the initial condition and the task specification, alleviating the need to repeat the costly pre-processing cycle for solving other scenarios, while allowing the incorporation of failure modes on-the-fly. Two case studies are provided: a simple one to showcase the concepts of the proposed methodology and a more elaborate one to demonstrate the effectiveness and validity of the methodology.

-- We study time-dependent dynamics on a network of order lattices, where structure-preserving lattice maps are used to fuse lattice-valued data over vertices and edges. The principal contribution is a novel asynchronous Laplacian, generalizing the usual graph Laplacian, adapted to a network of heterogeneous lattices. The resulting gossip algorithm is shown to converge asymptotically to stable "harmonic" distributions of lattice data. This general theorem is applicable to several general problems, including lattice-valued consensus, Kripke semantics, and threat detection, all using asynchronous local update rules. The use of the graph Laplacian to diffuse information over networks is well-established in classical and contemporary work ranging from opinion dynamics [1] to distributed multi-agent consensus [2] and control [3], synchronization [4], [5], flocking [6], and much more. In the past decade, Laplacians that are adapted to handle vector-valued data, such as graph connection Laplacians [7], [8] or matrix-weighted Laplacians [9], have been revolutionary in signal processing processing [10], [11] and machine learning [12], [13]. While the ultimate form of a generalized Laplacian is as yet not present in applications, there are hints of a broader theory finding its way from algebraic topology to data science. The Laplacian from calculus class and the graph Laplacian are two extreme examples of a Hodge Laplacian .

Trajectory prediction is essential for autonomous vehicles (AVs) to plan correct and safe driving behaviors. While many prior works aim to achieve higher prediction accuracy, few study the adversarial robustness of their methods. To bridge this gap, we propose to study the adversarial robustness of data-driven trajectory prediction systems. We devise an optimization-based adversarial attack framework that leverages a carefully-designed differentiable dynamic model to generate realistic adversarial trajectories. Empirically, we benchmark the adversarial robustness of state-of-the-art prediction models and show that our attack increases the prediction error for both general metrics and planning-aware metrics by more than 50% and 37%. We also show that our attack can lead an AV to drive off road or collide into other vehicles in simulation. Finally, we demonstrate how to mitigate the adversarial attacks using an adversarial training scheme.

Neural network-based driving planners have shown great promises in improving task performance of autonomous driving. However, it is critical and yet very challenging to ensure the safety of systems with neural network based components, especially in dense and highly interactive traffic environments. In this work, we propose a safety-driven interactive planning framework for neural network-based lane changing. To prevent over conservative planning, we identify the driving behavior of surrounding vehicles and assess their aggressiveness, and then adapt the planned trajectory for the ego vehicle accordingly in an interactive manner. The ego vehicle can proceed to change lanes if a safe evasion trajectory exists even in the predicted worst case; otherwise, it can stay around the current lateral position or return back to the original lane. We quantitatively demonstrate the effectiveness of our planner design and its advantage over baseline methods through extensive simulations with diverse and comprehensive experimental settings, as well as in real-world scenarios collected by an autonomous vehicle company.

Recently, distributed semi-supervised learning (DSSL) algorithms have shown their effectiveness in leveraging unlabeled samples over interconnected networks, where agents cannot share their original data with each other and can only communicate non-sensitive information with their neighbors. However, existing DSSL algorithms cannot cope with data uncertainties and may suffer from high computation and communication overhead problems. To handle these issues, we propose a distributed semi-supervised fuzzy regression (DSFR) model with fuzzy if-then rules and interpolation consistency regularization (ICR). The ICR, which was proposed recently for semi-supervised problem, can force decision boundaries to pass through sparse data areas, thus increasing model robustness. However, its application in distributed scenarios has not been considered yet. In this work, we proposed a distributed Fuzzy C-means (DFCM) method and a distributed interpolation consistency regularization (DICR) built on the well-known alternating direction method of multipliers to respectively locate parameters in antecedent and consequent components of DSFR. Notably, the DSFR model converges very fast since it does not involve back-propagation procedure and is scalable to large-scale datasets benefiting from the utilization of DFCM and DICR. Experiments results on both artificial and real-world datasets show that the proposed DSFR model can achieve much better performance than the state-of-the-art DSSL algorithm in terms of both loss value and computational cost.