Reinforcement learning (RL) demonstrates superior potential over traditional flight control methods for fixed-wing aircraft, particularly under extreme operational conditions. However, the high demand for training samples and the lack of efficient computation in existing simulators hinder its further application. In this paper, we introduce NeuralPlane, the first benchmark platform for large-scale parallel simulations of fixed-wing aircraft. NeuralPlane significantly boosts high-fidelity simulation via GPU-accelerated Flight Dynamics Model (FDM) computation, achieving a single-step simulation time of just 0.2 seconds at a parallel scale of $10^{6}$, far exceeding current platforms. We also provide clear code templates, comprehensive evaluation/visualization tools and hierarchical frameworks for integrating RL and traditional control methods. We believe that NeuralPlane can accelerate the development of RL-based fixed-wing flight control and serve as a new challenging benchmark for the RL community.

DePT induces a cone-shaped spatial-temporal attention prior,which injects theinformation propagation and aggregation principles and enables a global view. With physical constraint inductive bias baked into its design, our DePT is ready to plug and play for a broad class of multi-agent systems. The experimental results on one of the most challenging CPS - network-scale traffic signal control system in the open world - show that our model outperformed the state-of-the-art expert methods on synthetic and real-world datasets.

The world's first 360-degree drone is fun all around, if you don't mind the steep price or wearing goggles to control it. As someone who has been reviewing camera drones for over a decade, it's rare for me to encounter one that feels genuinely new. While DJI's continual stream of steadily improving, ever-reliable drones almost always impresses, what Antigravity has done with its first-ever product, the A1, essentially invents an entirely novel subcategory: the 360 drone. Using the same shoot-first, frame-later technology as the Insta360 X5 (Antigravity is technically a distinct company from Insta360, but the brands have close ties), the A1 has twin cameras to capture everything around it, allowing the user to reframe the footage later using mobile or desktop apps. Each of the cameras uses a 1/1.28-inch sensor and an ultrawide lens to capture a hemispherical view.

Abstract--For amputees with powered transfemoral prosthetics, navigating obstacles or complex terrain remains challenging. This study addresses this issue by using an inertial sensor on the sound ankle to guide obstacle-crossing movements. A genetic algorithm computes the optimal neural network structure to predict the required angles of the thigh and knee joints. A gait progression prediction algorithm determines the actuation angle index for the prosthetic knee motor, ultimately defining the necessary thigh and knee angles and gait progression. Results show that when the standard deviation of Gaussian noise added to the thigh angle data is less than 1, the method can effectively eliminate noise interference, achieving 100% accuracy in gait phase estimation under 150 Hz, with thigh angle prediction error being 8.71% and knee angle prediction error being 6.78%. These findings demonstrate the method's ability to accurately predict gait progression and joint angles, offering significant practical value for obstacle negotiation in powered transfemoral prosthetics.

Abstract-- This paper investigates a sample-based solution to the hybrid mode control problem across non-differentiable and algorithmic hybrid modes. Our approach reasons about a set of hybrid control modes as an integer-based optimization problem where we select what mode to apply, when to switch to another mode, and the duration for which we are in a given control mode. A sample-based variation is derived to efficiently search the integer domain for optimal solutions. We find our formulation yields strong performance guarantees that can be applied to a number of robotics-related tasks. In addition, our approach is able to synthesize complex algorithms and policies to compound behaviors and achieve challenging tasks. Last, we demonstrate the effectiveness of our approach in a real-world robotic examples that requires reactive switching between long-term planning and high-frequency control. I. INTRODUCTION Modern agile robotic systems must dynamically switch between discrete modes--such as making and breaking contacts--to synthesize complex behaviors like locomotion and manipulation.

Four-channel bilateral control is a method for achieving remote control with force feedback and adjustment operability by synchronizing the positions and forces of two manipulators. It is expected to significantly improve the operability of remote control for contact-rich tasks, and in recent years, it has also been used as a data collection method in imitation learning. Among these, the 4-channel bilateral control on the Cartesian coordinate system is advantageous in that it can be used for manipulators with different structures and that the dynamics in the Cartesian coordinate system can be adjusted by adjusting the control parameters, thus achieving intuitive operability for humans. However, achieving high operability by controlling a Cartesian coordinate system remains challenging. In the case of joint space control, all complex interactions between joints are treated as unknown disturbances, and a certain degree of control can be achieved by combining a linear control system with a classical single-input single-output (SISO) system. However, when designing a control system in the Cartesian coordinate system, the position and posture of the manipulator's end-effector are expressed in a three-dimensional special Euclidean group (SE(3)), which has different properties from the vector spaces commonly used in traditional control methods, such as noncommutativity and the fact that addition is not defined. Therefore, it is not possible to use classical control design methods that assume vector spaces as they are. It is possible to approximate the vector space and perform control based on the assumption that the posi-a) Correspondence to: yamane.koki.td@alumni.tsukuba.ac.jp

Abstract-- T elepresence robots enable users to interact with remote environments, but efficient and intuitive navigation remains a challenge. In this work, we developed and evaluated a shared control method, in which the robot navigates autonomously while allowing users to affect the path generation to better suit their needs. We compared this with control switching, where users toggle between direct and automated control. We hypothesized that shared control would maintain efficiency comparable to control switching while potentially reducing user workload. The results of two consecutive user studies (each with final sample of n = 20) showed that shared control does not degrade navigation efficiency, but did not show a significant reduction in task load compared to control switching. Further research is needed to explore the underlying factors that influence user preference and performance in these control systems. Telepresence robots represent a class of robotic systems in which a mobile robot is equipped with a camera streaming live video to a display that is watched by a remote user. These robots have already found a wide domain of applications ranging from business meetings and factory tours to personal events such as graduations and weddings. Furthermore, immersive-telepresence robots allow a panoramic camera stream to be watched by a remote user via a head-mounted display (HMD). These systems carry great potential in improving the user interaction with the remote environment, which is found to be lacking in the commercial systems [1].

Traffic congestion remains a significant challenge in modern urban networks. Autonomous driving technologies have emerged as a potential solution. Among traffic control methods, reinforcement learning has shown superior performance over traffic signals in various scenarios. However, prior research has largely focused on small-scale networks or isolated intersections, leaving large-scale mixed traffic control largely unexplored. This study presents the first attempt to use decentralized multi-agent reinforcement learning for large-scale mixed traffic control in which some intersections are managed by traffic signals and others by robot vehicles. Evaluating a real-world network in Colorado Springs, CO, USA with 14 intersections, we measure traffic efficiency via average waiting time of vehicles at intersections and the number of vehicles reaching their destinations within a time window (i.e., throughput). At 80% RV penetration rate, our method reduces waiting time from 6.17s to 5.09s and increases throughput from 454 vehicles per 500 seconds to 493 vehicles per 500 seconds, outperforming the baseline of fully signalized intersections. These findings suggest that integrating reinforcement learning-based control large-scale traffic can improve overall efficiency and may inform future urban planning strategies.

In this paper, we consider the distributed optimal control problem for discrete-time linear networked systems. In particular, we are interested in learning distributed optimal controllers using graph recurrent neural networks (GRNNs). Most of the existing approaches result in centralized optimal controllers with offline training processes. However, as the increasing demand of network resilience, the optimal controllers are further expected to be distributed, and are desirable to be trained in an online distributed fashion, which are also the main contributions of our work. To solve this problem, we first propose a GRNN-based distributed optimal control method, and we cast the problem as a self-supervised learning problem. Then, the distributed online training is achieved via distributed gradient computation, and inspired by the (consensus-based) distributed optimization idea, a distributed online training optimizer is designed. Furthermore, the local closed-loop stability of the linear networked system under our proposed GRNN-based controller is provided by assuming that the nonlinear activation function of the GRNN-based controller is both local sector-bounded and slope-restricted. The effectiveness of our proposed method is illustrated by numerical simulations using a specifically developed simulator.