Robotics and Autonomous Systems最新文献

The rapid development of robotics technology has driven the growth of robot types and the development of related technologies. As an important aspect of robot research, path planning technology plays an irreplaceable role in practical production and application. Ant colony algorithm has a wide range of applications in robot path planning, but there is also a problem of performance overly relying on initial parameter selection. In order to solve this problem and improve the performance of mobile robot path planning, an improved ant colony algorithm based on firefly algorithm was studied and designed in a two-dimensional environment. In order to further explore the performance of ant colony algorithm in solving robot coordinated path planning problems, an improved ant colony algorithm based on heuristic function was also designed. In a three-dimensional environment, an improved ant colony algorithm based on the improved artificial potential field method was designed. The research results show that the maximum running time of the improved ant colony algorithm based on the firefly algorithm in different grid environments is 819.36 s, 847.01 s, and 811.54 s, respectively. The average running time of the improved ant colony algorithm based on heuristic function in different grid environments is 5.19 s, 5.97 s, and 9.09 s, with average path lengths of 29.90 cm, 31.08 cm, and 37.01 cm, and path length variances of 0.35, 0.87, and 2.21, respectively. The ant colony algorithm based on the improved artificial potential field method has a running time of 1.930 s, 3.182 s, and 4.662 s in different grid environments, and a path length of 29.275 cm, 49.447 cm, and 67.057 cm, respectively. The ant colony algorithm for research and design optimization has good performance. The contribution of the research lies in the design of three path planning methods for mobile robots, including two-dimensional path planning and three-dimensional path planning, which improves the time of path planning and shortens the average path length. The novelty of the research is reflected in the design of a path planning method for mobile robots in two-dimensional and three-dimensional environments, which improves the ant colony algorithm through firefly algorithm and heuristic function, and combines the ant colony algorithm with the improved artificial potential field method. The method designed by the research institute can provide technical support for path planning of mobile robots.

This note scrutinizes an adaptive fault-tolerant control (FTC) approach tailored for unmanned aerial vehicles (UAVs), addressing the critical need for both fault accommodation and disturbance suppression. Departing from traditional reliance on robust discontinuous control strategies prone to chattering and demanding precise uncertainty bounds, our FTC method ensures fixed-time stability, guaranteeing the convergence of attitude tracking errors to zero. Central to our approach is an adaptive algorithm adept at concurrently estimating unknown actuator faults and upper bounds of lumped uncertainties. Moreover, our adaptive schemes accurately estimate the upper bound of the lumped uncertainty term, encompassing model uncertainties, external disturbances, and unmodeled dynamics, thereby eliminating the need for assuming known bounds on uncertainties. Stability analysis under the developed control law is thoroughly performed using the Lyapunov stability theory. Notably, our strategy employs an extended Kalman filter (EKF) observer for state estimation and fault detection, facilitating fault detection through an adaptive threshold technique dynamically adjusted based on real-time mean and variance of the residual signal. Through comprehensive simulation and experimental validations, our proposed methodology demonstrates significant advancements in ensuring safety and reliability in UAVs.

This paper presents adaptive and occupancy grid map algorithms for automatic lane change technology, a core technology in autonomous vehicles. The objectives are to improve driver safety and convenience with technology that automatically changes lanes at the request of the driver. The algorithms construct nine grids on the basis of ego vehicles and generate adaptive and occupancy grid maps by using the relative speeds of ego and target vehicles. When a driver requests a lane change, the adaptive grid map reduces the number of cases where the target vehicles may exist around the ego vehicle from 256 to 32, thus decreasing the calculation amount. Therefore, the algorithms are suitable for use in autonomous vehicles that require real-time calculations. An occupancy grid map is formed in accordance with the location of the target vehicles, and whether lane changes are possible is determined. The algorithms generate a virtual simulation environment with the CarMaker and are simulated using Matlab/Simulink. An experiment is conducted in a real driving environment with real vehicles to prove the validity of the algorithms.

© 2017 Elsevier Inc. All rights reserved.

We explore sim-to-real transfer of deep reinforcement learning controllers for a heavy vehicle with active suspensions designed for traversing rough terrain. While related research primarily focuses on lightweight robots with electric motors and fast actuation, this study uses a forestry vehicle with a complex hydraulic driveline and slow actuation. We simulate the vehicle using multibody dynamics and apply system identification to find an appropriate set of simulation parameters. We then train policies in simulation using various techniques to mitigate the sim-to-real gap, including domain randomization, action delays, and a reward penalty to encourage smooth control. In reality, the policies trained with action delays and a penalty for erratic actions perform nearly at the same level as in simulation. In experiments on level ground, the motion trajectories closely overlap when turning to either side, as well as in a route tracking scenario. When faced with a ramp that requires active use of the suspensions, the simulated and real motions are in close alignment. This shows that the actuator model together with system identification yields a sufficiently accurate model of the actuators. We observe that policies trained without the additional action penalty exhibit fast switching or bang–bang control. These present smooth motions and high performance in simulation but transfer poorly to reality. We find that policies make marginal use of the local height map for perception, showing no indications of predictive planning. However, the strong transfer capabilities entail that further development concerning perception and performance can be largely confined to simulation.

Underwater humanoid robots (UHRs) have emerged as a significant area of interest in robotics, with the potential to overcome the limitations of traditional underwater robots and revolutionize underwater activities. This review examines the development of UHRs, focusing on their perception, decision-making, and execution capabilities within a hierarchical human-machine cooperation framework. The Perception Layer involves gathering information from the environment and human collaborators. The Decision-making Layer explores different levels of robot autonomy and the current status of human-UHR collaborative decision-making. The Execution Layer encompasses modeling, control, and actuation mechanisms to translate high-level intentions into physical actions. Various UHR implementations across research teams are reviewed to provide a comprehensive overview of current advancements. Discussions and challenges surrounding UHR progress are provided as well. Continued research and development efforts of UHR represent a promising avenue for advancing human-machine cooperation and pushing the boundaries of underwater exploration, contributing to scientific discoveries and societal benefits in this captivating realm.

Online footstep planning is essential for bipedal walking robots, allowing them to walk in the presence of disturbances and sensory noise. Most of the literature on the topic has focused on optimizing the footstep placement while keeping the step timing constant. In this work, we introduce a footstep planner capable of optimizing footstep placement and step time online. The proposed planner, consisting of an Interior Point Optimizer (IPOPT) and an optimizer based on Augmented Lagrangian (AL) method with analytical gradient descent, solves the full dynamics of the Linear Inverted Pendulum (LIP) model in real time to optimize for footstep location as well as step timing at the rate of 200 Hz. We show that such asynchronous real-time optimization with the AL method (ARTO-AL) provides the required robustness and speed for successful online footstep planning. Furthermore, ARTO-AL can be extended to plan footsteps in 3D, allowing terrain-aware footstep planning on uneven terrains. Compared to an algorithm with no footstep time adaptation, our proposed ARTO-AL demonstrates increased stability in simulated walking experiments as it can resist pushes on flat ground and on a $10°$ ramp up to 120 N and 100 N respectively. Videos² and open-source code³ are released.

In the context of real world application, Search and Rescue Missions on the ocean surface remain a complex task due to the large-scale area and the forces of the ocean currents, spreading lost targets and debris in an unpredictable way. In this work, we present a Path Planning Approach to search for a lost target on ocean surface using a swarm of UAVs. The combination of GlobCurrent dataset and a Lagrangian simulator is used to determine where the particles are moved by the ocean currents forces while Deep Q-learning algorithm is applied to learn from their dynamics. The evaluation results of the trained models show that our search strategy is effective and efficient. Over a total search area (red Sea zone), surface of 453422 Km${}^2$, we have shown that our strategy Search Success Rate is 98.61%, the maximum Search Time to detection is 15 days and the average Search Time to detection is almost 15 h.

The recent success of hybrid methods in monocular odometry has led to many attempts to generalize the performance gains to hybrid monocular SLAM. However, most attempts fall short in several respects, with the most prominent issue being the need for two different map representations (local and global maps), with each requiring different, computationally expensive, and often redundant processes to maintain. Moreover, these maps tend to drift with respect to each other, resulting in contradicting pose and scene estimates, and leading to catastrophic failure. In this paper, we propose a novel approach that makes use of descriptor sharing to generate a single inverse depth scene representation. This representation can be used locally, queried globally to perform loop closure, and has the ability to re-activate previously observed map points after redundant points are marginalized from the local map, eliminating the need for separate map maintenance processes. The maps generated by our method exhibit no drift between each other, and can be computed at a fraction of the computational cost and memory footprint required by other monocular SLAM systems. Despite the reduced resource requirements, the proposed approach maintains its robustness and accuracy, delivering performance comparable to state-of-the-art SLAM methods (e.g., LDSO, ORB-SLAM3) on the majority of sequences from well-known datasets like EuRoC, KITTI, and TUM VI. The source code is available at: https://github.com/AUBVRL/fslam_ros_docker.

Adaptive informative path planning (AIPP) is important to many robotics applications, enabling mobile robots to efficiently collect useful data about initially unknown environments. In addition, learning-based methods are increasingly used in robotics to enhance adaptability, versatility, and robustness across diverse and complex tasks. Our survey explores research on applying robotic learning to AIPP, bridging the gap between these two research fields. We begin by providing a unified mathematical problem definition for general AIPP problems. Next, we establish two complementary taxonomies of current work from the perspectives of (i) learning algorithms and (ii) robotic applications. We explore synergies, recent trends, and highlight the benefits of learning-based methods in AIPP frameworks. Finally, we discuss key challenges and promising future directions to enable more generally applicable and robust robotic data-gathering systems through learning. We provide a comprehensive catalog of papers reviewed in our survey, including publicly available repositories, to facilitate future studies in the field.