This review research looks at recent advancements in intelligent travel route selection, cooperative vehicle infrastructure systems, and dynamic real-time navigation. It investigates the integration of cutting-edge te...
详细信息
Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information about the robot's morphology. The unde...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
Model-free reinforcement learning is a promising approach for autonomously solving challenging robotics control problems, but faces exploration difficulty without information about the robot's morphology. The under-exploration of multiple modalities with symmetric states leads to behaviors that are often unnatural and sub-optimal. This issue becomes particularly pronounced in the context of robotic systems with morphological symmetries, such as legged robots for which the resulting asymmetric and aperiodic behaviors compromise performance, robustness, and transferability to real hardware. To mitigate this challenge, we can leverage symmetry to guide and improve the exploration in policy learning via equivariance / invariance constraints. We investigate the efficacy of two approaches to incorporate symmetry: modifying the network architectures to be strictly equivariant / invariant, and leveraging data augmentation to approximate equivariant / invariant actor-critics. We implement the methods on challenging loco-manipulation and bipedal locomotion tasks and compare with an unconstrained baseline. We find that the strictly equivariant policy consistently outperforms other methods in sample efficiency and task performance in simulation. Additionaly, symmetry-incorporated approaches exhibit better gait quality, higher robustness and can be deployed zero-shot to hardware.
The Russia-Ukraine conflict has demonstrated that urban combat capability will become a core element determining the outcome of local wars. With the intelligent transformation of urban combat systems, their highly rel...
详细信息
ISBN:
(纸本)9798350379860;9798350379877
The Russia-Ukraine conflict has demonstrated that urban combat capability will become a core element determining the outcome of local wars. With the intelligent transformation of urban combat systems, their highly reliable, anti-interference, and robust communication networks have become the premise for instant "seamless communication" connecting various equipment platforms on the battlefield. Due to the characteristics of wireless self-organizing networks, such as decentralized networking, multi-hop long-distance transmission, and support for node mobility, they are widely used in the construction of terminal subnets for urban combat systems, enabling significant enhancements in human-computer interaction and collaborative reconnaissance and strike capabilities. This paper proposes an elastic networking topology control mechanism based on the Grey Wolf Optimizer algorithm for the network layer of self-organizing networks, and conducts simulation and comparative analysis. The results indicate that this method enhances the networking flexibility and network lifespan of self-organizing networks, ensuring reliable communication for urban combat.
In the task of generating images, various image generation models have been developed. 'Stable Diffusion' has garnered significant attention for its ability to generate high-quality derivative images with mini...
详细信息
This paper presents the test and validation of a shared control strategy for automated driving systems. Shared control involves collaboration between the driver and automation, allowing both parties to actively engage...
详细信息
ISBN:
(纸本)9798350399462
This paper presents the test and validation of a shared control strategy for automated driving systems. Shared control involves collaboration between the driver and automation, allowing both parties to actively engage and cooperate at different levels of the driving task. The involvement of the driver adds complexity to the control loop, necessitating comprehensive validation methodologies. The proposed approach focuses on two critical maneuvers: overtaking in low-visibility scenarios and lateral evasive actions. These maneuvers represent scenarios where striking a balance between safety and comfort is essential for driver acceptance. A modular architecture that integrates an arbitration module and the shared control algorithm is presented, primarily focusing on the lateral control of the vehicle. The validation is conducted using a dynamic simulator, involving 8 real drivers interacting with a virtual environment. The results demonstrate improved safety and user acceptance, indicating the effectiveness of the shared control strategies in comparison with no shared-control support. Future work involves implementing shared control in drive-by-wire systems to enhance both safety and driver comfort during critical maneuvers. Overall, this research contributes to the development and validation of shared control approaches in automated driving systems.
This paper proposes a novel vehicle convoy control driving with efficient driving manoeuvers such as coasting and regeneration to reduce CO2 emissions. This control assumes a near-future traffic situation where there ...
详细信息
ISBN:
(纸本)9798350399462
This paper proposes a novel vehicle convoy control driving with efficient driving manoeuvers such as coasting and regeneration to reduce CO2 emissions. This control assumes a near-future traffic situation where there are automated and driving vehicles. A control method that drastically reduces CO2 emissions for each group of vehicles including following manual driving vehicles is established by simplifying the problem by going back to the principles to realize a control with a low calculation time in anticipation of utilization in actual vehicles. This simplification makes it possible to properly control the entire vehicle convoy by referring to control maps that are derived through traffic flow simulation. Energy consumption reduction by the proposed control strategy has been verified with simulation, showing a 6.4% reduction for battery electric vehicles under the condition that the controlled vehicle with its following vehicles passes through an intersection.
In this paper, we present a novel study on a BEV (bird's eye view) image-based lane tracking control system for an autonomous lane repainting robot. Our research introduces a cutting-edge lane detection method bas...
详细信息
ISBN:
(纸本)9798350377712;9798350377705
In this paper, we present a novel study on a BEV (bird's eye view) image-based lane tracking control system for an autonomous lane repainting robot. Our research introduces a cutting-edge lane detection method based on BEV images, leveraging row-anchor techniques to enhance precision and provide detailed error information for lane tracking algorithms. By utilizing real-time sensor data and advanced deep learning processes, we have successfully implemented a high-performance lane repainting system that minimizes errors and ensures accuracy. Our proposed position-based visual pure pursuit algorithm (PV-PP) plays a crucial role in guiding the lane repainting process with precision and efficiency, ultimately improving the functionality and feasibility of the linear actuator responsible for paint spraying in the real indusrial fields. Through our contributions, including innovative lane detection methods, real-time sensor utilization, and robot control algorithm design, we aim to advance the field of autonomous lane repainting robots and enhance the safety and effectiveness of road maintenance operations.
Non-Fungible Tokens (NFTs) are cryptographic assets on a blockchain. Blockchain by definition is a public ledger. NFTs are becoming a tool to collect and share digital art as well as providing an investment opportunit...
详细信息
This research investigates the performance of 6G communication systems operating in millimeter-wave and sub-THz frequency bands. The study focuses on evaluating the performance of massive MIMO systems with both unifor...
详细信息
A distributed computing paradigm known as 'cloud computing' uses the Internet to deliver computing-that is, processing, storage, services, networks, and applications-in a controlled, virtualized, abstracted, a...
详细信息
暂无评论