GNSS localization using everyday mobile devices is challenging in urban environments, as ranging errors caused by the complex propagation of satellite signals and low-quality onboard GNSS hardware are blamed for undermining positioning accuracy. Researchers have pinned their hopes on data-driven methods to regress such ranging errors from raw measurements. However, the grueling annotation of ranging errors impedes their pace. This paper presents a robust end-to-end Neural Ranging Correction (NeRC) framework, where localization-related metrics serve as the task objective for training the neural modules. Instead of seeking impractical ranging error labels, we train the neural network using ground-truth locations that are relatively easy to obtain. This functionality is supported by differentiable moving horizon location estimation (MHE) that handles a horizon of measurements for positioning and backpropagates the gradients for training. Even better, as a blessing of end-to-end learning, we propose a new training paradigm using Euclidean Distance Field (EDF) cost maps, which alleviates the demands on labeled locations. We evaluate the proposed NeRC on public benchmarks and our collected datasets, demonstrating its distinguished improvement in positioning accuracy. We also deploy NeRC on the edge to verify its real-time performance for mobile devices.

Helmet-mounted wearable positioning systems are crucial for enhancing safety and facilitating coordination in industrial, construction, and emergency rescue environments. These systems, including LiDAR-Inertial Odometry (LIO) and Visual-Inertial Odometry (VIO), often face challenges in localization due to adverse environmental conditions such as dust, smoke, and limited visual features. To address these limitations, we propose a novel head-mounted Inertial Measurement Unit (IMU) dataset with ground truth, aimed at advancing data-driven IMU pose estimation. Our dataset captures human head motion patterns using a helmet-mounted system, with data from ten participants performing various activities. We explore the application of neural networks, specifically Long Short-Term Memory (LSTM) and Transformer networks, to correct IMU biases and improve localization accuracy. Additionally, we evaluate the performance of these methods across different IMU data window dimensions, motion patterns, and sensor types. We release a publicly available dataset, demonstrate the feasibility of advanced neural network approaches for helmet-based localization, and provide evaluation metrics to establish a baseline for future studies in this field. Data and code can be found at https://lqiutong.github.io/HelmetPoser.github.io/.

A differential dynamic programming (DDP)-based framework for inverse reinforcement learning (IRL) is introduced to recover the parameters in the cost function, system dynamics, and constraints from demonstrations. Different from existing work, where DDP was usually used for the inner forward problem, our proposed framework uses it to efficiently compute the gradient required in the outer inverse problem with equality and inequality constraints. The equivalence between the proposed and existing methods based on Pontryagin's Maximum Principle (PMP) is established. More importantly, using this DDP-based IRL with an open-loop loss function, a closed-loop IRL framework is presented. In this framework, a loss function is proposed to capture the closed-loop nature of demonstrations. It is shown to be better than the commonly used open-loop loss function. We show that the closed-loop IRL framework reduces to a constrained inverse optimal control problem under certain assumptions. Under these assumptions and a rank condition, it is proven that the learning parameters can be recovered from the demonstration data. The proposed framework is extensively evaluated through four numerical robot examples and one real-world quadrotor system. The experiments validate the theoretical results and illustrate the practical relevance of the approach.

The pseudorange error is one of the root causes of localization inaccuracy in GPS. Previous data-driven methods regress and eliminate pseudorange errors using handcrafted intermediate labels. Unlike them, we propose an end-to-end GPS localization framework, E2E-PrNet, to train a neural network for pseudorange correction (PrNet) directly using the final task loss calculated with the ground truth of GPS receiver states. The gradients of the loss with respect to learnable parameters are backpropagated through a Differentiable Nonlinear Least Squares (DNLS) optimizer to PrNet. The feasibility of fusing the data-driven neural network and the model-based DNLS module is verified with GPS data collected by Android phones, showing that E2E-PrNet outperforms the baseline weighted least squares method and the state-of-the-art end-to-end data-driven approach. Finally, we discuss the explainability of E2E-PrNet.

This article investigates the similar formation control problem for multirobot systems. Specifically, we propose an integrated relative localization and similar formation control scheme to navigate multirobot systems to a desired configuration, which is a similar transformation of a given template, based on interrobot and robot-landmark range measurements and odometry measurements of robots themselves. To achieve the exact relative localization, a persistent excitation (P.E.) signal is introduced in the controller which, however, perturbs the motion of each robot and affects the formation accuracy. To resolve the conflict, an autonomous system with its output regulated by a carefully designed function of range measurements is introduced to generate the persistent excitation. It is proved that the similar formation control problem can be solved by our proposed scheme with global asymptotic convergence for directed acyclic graphs (DAGs). Both numerical simulation and physical experiment are presented to verify and validate the effectiveness of our theoretical findings.

Deep learning has had remarkable success in robotic perception, but its data-centric nature suffers when it comes to generalizing to ever-changing environments. By contrast, physics-based optimization generalizes better, but it does not perform as well in complicated tasks due to the lack of high-level semantic information and reliance on manual parametric tuning. To take advantage of these two complementary worlds, we present PyPose: a robotics-oriented, PyTorch-based library that combines deep perceptual models with physics-based optimization. PyPose's architecture is tidy and well-organized, it has an imperative style interface and is efficient and user-friendly, making it easy to integrate into real-world robotic applications. Besides, it supports parallel computing of any order gradients of Lie groups and Lie algebras and 2nd-order optimizers, such as trust region methods. Experiments show that PyPose achieves more than 10× speedup in computation compared to the state-of-the-art libraries. To boost future research, we provide concrete examples for several fields of robot learning, including SLAM, planning, control, and inertial navigation.

In this paper, we present the dynamic model and control of DoubleBee, a novel hybrid aerial-ground vehicle consisting of two propellers mounted on tilting servo motors and two motor-driven wheels. DoubleBee exploits the high energy efficiency of a bicopter configuration in aerial mode, and enjoys the low power consumption of a two-wheel self-balancing robot on the ground. Furthermore, the propeller thrusts act as additional control inputs on the ground, enabling a novel decoupled control scheme where the attitude of the robot is controlled using thrusts and the translational motion is realized using wheels. A prototype of DoubleBee is constructed using commercially available components. The power efficiency and the control performance of the robot are verified through comprehensive experiments. Challenging tasks in indoor and outdoor environments demonstrate the capability of DoubleBee to traverse unstructured environments, fly over and move under barriers, and climb steep and rough terrains.

This brief proposes a game-theoretic inverse reinforcement learning (GT-IRL) framework, which aims to learn the parameters in both the dynamic system and individual cost function of multistage games from demonstrated trajectories. Different from the probabilistic approaches in computer science community and residual minimization solutions in control community, our framework addresses the problem in a deterministic setting by differentiating Pontryagin's maximum principle (PMP) equations of open-loop Nash equilibrium (OLNE), which is inspired by Jin et al. (2020). The differentiated equations for a multi-player nonzero-sum multistage game are shown to be equivalent to the PMP equations for another affine-quadratic nonzero-sum multistage game and can be solved by some explicit recursions. A similar result is established for two-player zero-sum games. Simulation examples are presented to demonstrate the effectiveness of our proposed algorithms.

Despite recent progress in trajectory planning for multiple robots and a single tethered robot, trajectory planning for multiple tethered robots to reach their individual targets without entanglements remains a challenging problem. In this article, a complete approach is presented to address this problem. First, a multirobot tether-aware representation of homotopy is proposed to efficiently evaluate the feasibility and safety of a potential path in terms of 1) the cable length required to reach a target following the path, and 2) the risk of entanglements with the cables of other robots. Then the proposed representation is applied in a decentralized and online planning framework, which includes a graph-based kinodynamic trajectory finder and an optimization-based trajectory refinement, to generate entanglement-free, collision-free, and dynamically feasible trajectories. The efficiency of the proposed homotopy representation is compared against the existing single and multiple tethered robot planning approaches. Simulations with up to eight UAVs show the effectiveness of the approach in entanglement prevention and its real-time capabilities. Flight experiments using three tethered UAVs verify the practicality of the presented approach. The software implementation is publicly available online.1

This article studies the problem of distributed framework matching (FM), which originates from the assignment task in multirobot coordination and the matching task in pattern recognition. The objective of distributed FM is to distributively seek a correspondence which minimizes some metrics describing the disagreement between two frameworks (i.e., graphs and their embeddings). In view of the type of the underlying graph in the framework, two formulations, undirected framework matching (UFM) and directed framework matching (DFM), and their convex relaxations, relaxed UFM (RUFM), and relaxed DFM (RDFM), are presented. UFM is converted into a graph matching (GM) problem with the adjacency matrix being replaced by a matrix constructed from the undirected framework under certain graphical conditions, and can be solved distributively. Sufficient conditions for the equivalence between UFM and RUFM, and the perturbation admitting exact recovery of correspondence are established. On the other hand, DFM embeds the configuration of the directed framework via another type of matrix, whose computation is distributed, and can deal with the case of two frameworks with different sizes of node sets. A distributed optimization algorithm for solving RDFM is proposed and its convergence results are established which allows DFM to be solved in a fully distributed manner. Simulation examples on both synthetic data and real world datasets demonstrate the applicability and efficacy of our theoretical results in formation control and object matching problems.

In this article, we consider the problem of using a multirobot system to conduct sweep coverage over a region with uneven and unknown workload distribution. Uneven workload distribution means that a robot has to spend different amounts of time covering a unit area at different locations in the region. Unknown workload distribution means that the amount of workload at any location is unknown prior to the operation, hence online sensing and allocation of workload is needed for better efficiency. In this work, we adopt the formulation in which the entire region is separated into multiple stripes, and a discrete-time distributed workload allocation algorithm is used to allocate workload on a stripe to each robot. Previous works that adopt similar formulations do not provide rigorous stability analysis and experimental verification and lack consideration of practical aspects, such as limited sensor range. This work addresses these weaknesses and bridges the gap between theory and practice. First, compared with the existing works, the convergence of the distributed workload allocation algorithm to the optimal workload assignment is established under a more realistic assumption, and less conservative error bounds are derived, which serve as a better indicator of the effectiveness of the algorithm. Second, we propose a new algorithm that addresses the limited sensor range of robots, which is an important constraint in applications, such as agricultural spraying and building inspection. The stability analysis and error bound of the proposed algorithm are also provided. Third, realistic simulations and actual flight experiments using unmanned aerial vehicles are carried out to demonstrate the practicality and validate the theoretical results.

This paper studies the dynamic formation control problem for cooperative agents with discrete-time dynamics over directed graphs. Unlike using absolute coordinate, relative coordinate, interagent distance, or interagent bearing to specify the target formation and coordinate agents to achieve the formation, we study a coordination problem where the desired formation varies with time and only its geometric shape is predefined. Matrix-valued Laplacian approach has been adopted to address this problem in the continuous-time setting. However, the discrete-time counterpart is more challenging due to the constraint in information exchange. On the other hand, observe that in many real operations, at a given time instant, the agents will be able to plan their target formation configurations for a period of time ahead. We propose preview-based P-like and PD-like controllers for the formation control. The controllers with proper parameter setting are proved to be effective to address the dynamic formation control problem. Numerical simulations are given to validate the effectiveness of the proposed controllers.

This paper presents a notion of rigidity, Ratio-of-Distance (RoD) rigidity, for studying when a framework can be uniquely determined by a set of RoD constraints up to similar transformations. Unlike the constraints such as distance, bearing and angle used in existing literature, we aim to develop a framework by a set of RoD constraints (the ratio of distances of a pair of edges joining a common vertex). In particular, triangulated Laman graphs are introduced to provide some sufficient conditions for the RoD rigidity. The proposed RoD rigidity theory is further applied to the RoD-based similar formation control. Numerical simulations are provided to support the analysis.