Journal of Intelligent & Robotic Systems最新文献

The Paris Olympics and Paralympics are scheduled to take place between 26 July and 8 September 2024, whereby electric vertical take-off and landing aircraft are anticipated to take to the skies to offer a new mobility solution to spectators of the Games. This will allow paying members of the public to move between different points within the Paris region akin to an on-demand taxi service, but through the air; passenger air taxi services (PATS). These passengers, as consumers, will have certain rights and duties under European Union law. To determine the level of protection afforded to these air passengers, a full assessment of Regulation (EC) No 261/2004 is required. As the revision of the Regulation is currently on the European Commission’s agenda, it is also important to consider its revision in light of PATS, whereby new technology, emerging business practices, changing customer behaviour and societal expectations for the level of legal protection of PATS users must be considered. This article will, therefore, assess the current version of the Regulation, in light of the interpretation from the European Court, to see whether it applies to PATS and, if so, whether it is suitable or if specific amendments need to be added to the planned revised Regulation.

Recent advancements in AI and deep learning have created a growing demand for artificial agents capable of performing tasks within increasingly complex environments. To address the challenges associated with continuous learning constraints and knowledge capacity in this context, cognitive architectures inspired by human cognition have gained significance. This study contributes to existing research by introducing a cognitive-attentional system employing a constructive neural network-based learning approach for continuous acquisition of procedural knowledge. We replace an incremental tabular Reinforcement Learning algorithm with a constructive neural network deep reinforcement learning mechanism for continuous sensorimotor knowledge acquisition, thereby enhancing the overall learning capacity. The primary emphasis of this modification centers on optimizing memory utilization and reducing training time. Our study presents a learning strategy that amalgamates deep reinforcement learning with procedural learning, mirroring the incremental learning process observed in human sensorimotor development. This approach is embedded within the CONAIM cognitive-attentional architecture, leveraging the cognitive tools of CST. The proposed learning mechanism allows the model to dynamically create and modify elements in its procedural memory, facilitating the reuse of previously acquired functions and procedures. Additionally, it equips the model with the capability to combine learned elements to effectively adapt to complex scenarios. A constructive neural network was employed, initiating with an initial hidden layer comprising one neuron. However, it possesses the capacity to adapt its internal architecture in response to its performance in procedural and sensorimotor learning tasks, inserting new hidden layers or neurons. Experimentation conducted through simulations involving a humanoid robot demonstrates the successful resolution of tasks that were previously unsolved through incremental knowledge acquisition. Throughout the training phase, the constructive agent achieved a minimum of 40% greater rewards and executed 8% more actions when compared to other agents. In the subsequent testing phase, the constructive agent exhibited a 15% increase in the number of actions performed in contrast to its counterparts.

Flip ambiguities are a notorious issue with distance-based formation control due to the presence of unwanted equilibrium points in the formation dynamics. We propose a switched control system for preventing these ambiguities in 3D formations composed of tetrahedra. The approach contains a switching strategy that steers the formation of mobile robots towards the desired configuration for all initial positions, excluding certain collocated, collinear, or coplanar cases, by applying the standard distance-based controller and/or rigid-body maneuvers to subformations. Simulations demonstrate that the proposed formation control system can lead to faster formation acquisition and less control effort than an existing method.

Urban Air Mobility (UAM) is an emerging air traffic system designed for passengers and cargo in and around urban environments. Both the Federal Aviation Administration of the United States and the European Union Aviation Safety Agency endorse a phased development approach for UAM, commencing with manned aviation and subsequently transitioning to remotely piloted and autonomous operations. This article focuses on legal considerations related to aviation safety, with a specific focus on pilot licensing and crew fatigue management. An analysis of existing aviation law provisions suggests that the International Civil Aviation Organization can work with local authorities to create regulations governing both on-board and remote pilots involved in UAM operations. Safety standards in air law can apply mutatis mutandis to on-board pilots until specific regulations are developed. In the longer term, there shall be domestic laws on both on-board and remote UAM pilots.

Bridge inspection is currently a labor intensive task. Utilizing unmanned aerial vehicles (UAVs) to assist in inspection tasks is a promising direction. However, enabling UAVs for autonomous inspection involves the UAV state estimation problems. Since parts of UAV sensors could be unavailable, how to estimate states via sensor fusion is the key. In this paper, we propose a tightly-coupled nonlinear optimization-based system that integrates four kinds of sensors: camera, IMU, Ultra-wideband (UWB) range measurements, and global navigation satellite system (GNSS). Due to the tightly-coupled multi-sensor fusion method and system design, the system takes the advantage of the four sensors, and can seamlessly respond to indoor and outdoor GNSS and UWB loss or reacquisition. It can effectively reduce the long-term trajectory drift and provide smooth and continuous state estimation. The experimental results show that the proposed method outperforms the state-of-the-art approaches.

Considering the nonlinearity and unknown dynamics of fixed-wing unmanned aerial vehicles in perched landing maneuvers, an event-based online guidance and incremental control scheme is proposed. The guidance trajectory for perched landing must be dynamically feasible therefore an event-based trapezoidal collocation point optimization method is proposed. Introduction of the triggering mechanism for the rational use of computing resources to improve PL accuracy. Furthermore, a filter-based incremental nonlinear dynamic inverse (F-INDI) control with state transformation is proposed to achieve robust trajectory tracking under high angle of attack (AOA). The F-INDI uses low-pass filters to obtain incremental dynamics of the system, which simplifies the design process. The state transformation strategy is to convert the flight-path angle, AOA and velocity into two composite dynamics, which avoids the sign reversal problem of control gain under high AOA. The stability analysis shows that the original states can be controlled only by controlling the composite state. Simulation results show that the proposed scheme achieves high perched landing accuracy and a reliable trajectory tracking control.

This paper studies the modeling and control of a Planar Vertical Take-Off and Landing (PVTOL) with steerable thruster. A longitudinal model is obtained using Newton’s second law for the PVTOL which evolves in 3 degrees of freedom and has two control inputs. The aerial vehicle is driven by steerable propulsion controlling its evolution in the vertical plane through the thrust and torque control inputs, which drive the vehicle body and generate a rotation. The obtained model is nonlinear and is significantly different with respect to the well-known PVTOL. For this reason, different control algorithms are presented, and the closed-loop behavior is studied for each of them. The proposed control strategies perform a stationary flight at a desired altitude and control the position of the aerial vehicle. The performance of the proposed control algorithms is tested in numerical simulations.

In this paper we propose a learning-based restoration approach to learn the optimal parameters for enhancing the quality of different types of underwater images and apply a set of intensity transformation techniques to process raw underwater images. The methodology comprises two steps. Firstly, a Convolutional Neural Network (CNN) Regression model is employed to learn enhancing parameters for each underwater image type. Trained on a diverse dataset, the CNN captures complex relationships, enabling generalization to various underwater conditions. Secondly, we apply intensity transformation techniques to raw underwater images. These transformations collectively compensate for visual information loss due to underwater degradation, enhancing overall image quality. In order to evaluate the performance of our proposed approach, we conducted qualitative and quantitative experiments using well-known underwater image datasets (U45 and UIEB), and using the proposed challenging dataset composed by 276 underwater images from the Amazon region (AUID). The results demonstrate that our approach achieves an impressive accuracy rate in different underwater image datasets. For U45 and UIEB datasets, regarding PSNR and SSIM quality metrics, we achieved 26.967, 0.847, 27.299 and 0.793, respectively. Meanwhile, the best comparison techniques achieved 26.879, 0.831, 27.157 and 0.788, respectively.

Abstract

As rigid robots suffer from the higher inertia of their rigid links, cable-driven parallel robots (CDPRs) are more suitable for large-scale three-dimensional (3D) printing tasks due to their outstanding reconfigurability, high load-to-weight ratio, and extensive workspace. In this paper, a parallel 3D printing robot is proposed, comprising three pairs of driving cables to control the platform motion and three pairs of redundant cables to adjust the cable tension. To improve the motion accuracy of the moving platform, the static kinematic error model is established, and the error sensitivity coefficient is determined to reduce the dimensionality of the optimization function. Subsequently, the self-calibration positions are determined based on the maximum cable length error in the reachable workspace. A self-calibration method is proposed based on the genetic algorithm to solve the kinematic parameter deviations. Additionally, the dynamic errors are effectively reduced by compensating for the elastic deformation errors of the cable lengths. Furthermore, an experimental prototype is developed. The results of dynamic error compensation after the self-calibration indicate a 67.4% reduction in terms of the maximum error along the Z-axis direction. Finally, the developed prototype and proposed calibration and compensation methods are validated through the printing experiment.

This paper introduces 3-D surface tracking control of an Unmanned Underwater Vehicle (UUV) in tunnel-like environments. Consider the case where a sonar transducer in the UUV does not rotate, and it only emits fixed sonar ray reporting a simple distance measurement. This reduces the power consumption of the UUV, while reducing the UUV’s size and price. The UUV is controlled to proceed in tunnel-like environments, while maintaining a predefined distance from the tunnel boundaries. For maintaining a predefined distance from tunnel boundaries, the UUV uses fixed sonar rays surrounding it. As far as we know, our article is novel in developing 3-D surface tracking controls of tunnel-like environments utilizing an UUV with fixed sonar rays surrounding it. MATLAB simulations are used for demonstrating the performance of the proposed tracking controls.