scispace - formally typeset
Search or ask a question

Showing papers on "Obstacle avoidance published in 2021"


Journal ArticleDOI
Kai Zhu1, Tao Zhang1
TL;DR: This paper systematically compares and analyzes the relationship and differences between four typical application scenarios: local obstacle avoidance, indoor navigation, multi-robot navigation, and social navigation; and describes the development of DRL-based navigation.

117 citations


Journal ArticleDOI
TL;DR: This article builds an end-to-end deep neural network that takes as input a pair of RGB and thermal images and outputs pixel-wise semantic labels and demonstrates that the experimental results demonstrate that the network outperforms the state-of-the-art networks.
Abstract: Semantic segmentation of urban scenes is an essential component in various applications of autonomous driving. It makes great progress with the rise of deep learning technologies. Most of the current semantic segmentation networks use single-modal sensory data, which are usually the RGB images produced by visible cameras. However, the segmentation performance of these networks is prone to be degraded when lighting conditions are not satisfied, such as dim light or darkness. We find that thermal images produced by thermal imaging cameras are robust to challenging lighting conditions. Therefore, in this article, we propose a novel RGB and thermal data fusion network named FuseSeg to achieve superior performance of semantic segmentation in urban scenes. The experimental results demonstrate that our network outperforms the state-of-the-art networks. Note to Practitioners —This article investigates the problem of semantic segmentation of urban scenes when lighting conditions are not satisfied. We provide a solution to this problem via information fusion with RGB and thermal data. We build an end-to-end deep neural network, which takes as input a pair of RGB and thermal images and outputs pixel-wise semantic labels. Our network could be used for urban scene understanding, which serves as a fundamental component of many autonomous driving tasks, such as environment modeling, obstacle avoidance, motion prediction, and planning. Moreover, the simple design of our network allows it to be easily implemented using various deep learning frameworks, which facilitates the applications on different hardware or software platforms.

96 citations


Journal ArticleDOI
TL;DR: In this paper, a deep reinforcement learning-based method for UAV obstacle avoidance is proposed to enable a UAV quadrotor to autonomously avoid collisions with obstacles in unstructured and unknown indoor environments.
Abstract: This paper presents our method for enabling a UAV quadrotor, equipped with a monocular camera, to autonomously avoid collisions with obstacles in unstructured and unknown indoor environments. When compared to obstacle avoidance in ground vehicular robots, UAV navigation brings in additional challenges because the UAV motion is no more constrained to a well-defined indoor ground or street environment. Unlike ground vehicular robots, a UAV has to navigate across more types of obstacles - for e.g., objects like decorative items, furnishings, ceiling fans, sign-boards, tree branches, etc., are also potential obstacles for a UAV. Thus, methods of obstacle avoidance developed for ground robots are clearly inadequate for UAV navigation. Current control methods using monocular images for UAV obstacle avoidance are heavily dependent on environment information. These controllers do not fully retain and utilize the extensively available information about the ambient environment for decision making. We propose a deep reinforcement learning based method for UAV obstacle avoidance (OA) which is capable of doing exactly the same. The crucial idea in our method is the concept of partial observability and how UAVs can retain relevant information about the environment structure to make better future navigation decisions. Our OA technique uses recurrent neural networks with temporal attention and provides better results compared to prior works in terms of distance covered without collisions. In addition, our technique has a high inference rate and reduces power wastage as it minimizes oscillatory motion of UAV.

92 citations


Journal ArticleDOI
TL;DR: This paper studies a new coupled fractional-order sliding mode control (CFSMC) and obstacle avoidance scheme, which has superior capacities of providing more control flexibilities and achieving high-accuracy.
Abstract: Recently, four-wheeled steerable mobile robots (FSMR) have attracted increasing attention in industrial fields, however the collision-free trajectory tracking control is still challenging in dynamic environments. This paper studies a new coupled fractional-order sliding mode control (CFSMC) and obstacle avoidance scheme, which has superior capacities of providing more control flexibilities and achieving high-accuracy. Instead of exploring traditional integer-order solutions, novel fractional-order sliding surfaces are proposed to handle the nonlinear interconnected states in a coupled structure. To accomplish non-oscillating avoidance of both stationary and moving entities within an uncertain workspace, a modified near-time-optimal potential function is subsequently presented with improved efficiency and reduced collision-resolving distances. By utilizing fuzzy rules, proper adaption gains of the reaching laws are designed to degenerate the effect of undesired chattering. The asymptotic stability and convergence can be guaranteed for the resultant closed-loop system. Three experiments are implemented on a real-time FSMR system. The results validate the reliability of the presented CFSMC scheme in terms of significantly mitigated following errors, faster disturbance rejection and smooth transition as compared to conventional methods.

86 citations


Journal ArticleDOI
01 Jan 2021
TL;DR: By assuming other agents respecting the same CBF condition, the supervisory control algorithm can be implemented decentrally and guarantees obstacle avoidance for all agents and is applicable to general nonlinear robot dynamics and is scalable to an arbitrary number of agents.
Abstract: This letter considers the problem of obstacle avoidance for multiple robotic agents moving in an environment with obstacles. A decentralized supervisory controller is synthesized based on control barrier functions (CBF) that guarantees obstacle avoidance with limited actuation capability. The proposed method is applicable to general nonlinear robot dynamics and is scalable to an arbitrary number of agents. Agent-to-agent communication is not required, yet a simple broadcasting scheme improves the performance of the algorithm. The key idea is based on a control barrier function constructed with a backup controller, and we show that by assuming other agents respecting the same CBF condition, the supervisory control algorithm can be implemented decentrally and guarantees obstacle avoidance for all agents.

84 citations


Journal ArticleDOI
TL;DR: These path planning algorithms that deal with constraints and characteristics of AUV and the influence of marine environments are described and some potential future research directions that are worthy to investigate in this field are proposed.

78 citations


Journal ArticleDOI
TL;DR: The proposed formation generation algorithm implements an approach combining a virtual structure and artificial potential field (VSAPF), which provides a high accuracy of formation shape keeping and flexibility of formationshape change, which has the advantage of less calculations.
Abstract: This paper proposes a formation generation algorithm and formation obstacle avoidance strategy for multiple unmanned surface vehicles (USVs) The proposed formation generation algorithm implements an approach combining a virtual structure and artificial potential field (VSAPF), which provides a high accuracy of formation shape keeping and flexibility of formation shape change To solve the obstacle avoidance problem of the multi-USV system, an improved dynamic window approach is applied to the formation reference point, which considers the movement ability of the USV By applying this method, the USV formation can avoid obstacles while maintaining its shape The combination of the virtual structure and artificial potential field has the advantage of less calculations, so that it can ensure the real-time performance of the algorithm and convenience for deployment on an actual USV Various simulation results for a group of USVs are provided to demonstrate the effectiveness of the proposed algorithms

66 citations


Proceedings ArticleDOI
22 Apr 2021
TL;DR: In this paper, the authors propose a framework for object manipulation built upon the physics-enabled, visually rich AI2-THOR framework and present a new challenge to the Embodied AI community known as ArmPointNav.
Abstract: The domain of Embodied AI has recently witnessed substantial progress, particularly in navigating agents within their environments. These early successes have laid the building blocks for the community to tackle tasks that require agents to actively interact with objects in their environment. Object manipulation is an established research domain within the robotics community and poses several challenges including manipulator motion, grasping and long-horizon planning, particularly when dealing with oft-overlooked practical setups involving visually rich and complex scenes, manipulation using mobile agents (as opposed to tabletop manipulation), and generalization to unseen environments and objects. We propose a framework for object manipulation built upon the physics-enabled, visually rich AI2-THOR framework and present a new challenge to the Embodied AI community known as ArmPointNav. This task extends the popular point navigation task [2] to object manipulation and offers new challenges including 3D obstacle avoidance, manipulating objects in the presence of occlusion, and multi-object manipulation that necessitates long term planning. Popular learning paradigms that are successful on PointNav challenges show promise, but leave a large room for improvement.

63 citations


Journal ArticleDOI
TL;DR: In this article, an online path planning approach for UAV is developed based on deep reinforcement learning, which can achieve the perception of the environment and continuous motion output control through end-to-end learning powered by neural networks, aiming to address the control problem of maneuvering target tracking and obstacle avoidance.

62 citations


Journal ArticleDOI
TL;DR: A novel hierarchical framework for the flexible motion of the six wheel-legged robot (BIT-6NAZA) is considered, indicating that it is a superior case of a selectable flexible motion with satisfactory stable performance under the field world environment.
Abstract: In complex real-world scenarios, wheel-legged robots with maneuverability, stability and reliability have addressed growing research attention, especially in material transportation, emergency rescue, as well as the exploration of unknown environments. How to achieve stable high-level movement with payload delivery simultaneously is the main challenge for the wheel-legged robot. In this paper, a novel hierarchical framework for the flexible motion of the six wheel-legged robot is considered in experimental results. Firstly, for the wheeled motion, the speed consensus algorithm is implemented to the six-wheeled cooperative control; for the legged motion, three gait sequences and foot-end trajectory based on the Bezier function are designed. Furthermore, a whole-body control architecture includes the attitude controller, impedance controller and center height controller is developed for obstacle avoidance, which can ensure the horizontal stability of the body of the robot when it passes through obstacles in different terrain. Finally, extensive experimental demonstrations using the six wheel-legged robot (BIT-6NAZA) are dedicated to the effectiveness and robustness of the developed framework, indicating that it is a superior case of a selectable flexible motion with satisfactory stable performance under the field world environment.

61 citations


Journal ArticleDOI
TL;DR: A robust nonlinear model predictive control scheme is presented for the case of underactuated autonomous underwater vehicles (AUVs) and is presented a reliable control strategy that takes into account the aforementioned issues, along with dynamic uncertainties of the model and the presence of ocean currents.
Abstract: This article addresses the tracking control problem of 3-D trajectories for underactuated underwater robotic vehicles operating in a constrained workspace including obstacles More specifically, a robust nonlinear model predictive control (NMPC) scheme is presented for the case of underactuated autonomous underwater vehicles (AUVs) (ie, unicycle-like vehicles actuated only in the surge, heave, and yaw) The purpose of the controller is to steer the unicycle-like AUV to the desired trajectory with guaranteed input and state constraints (eg, obstacles, predefined vehicle velocity bounds, and thruster saturations) inside a partially known and dynamic environment where the knowledge of the operating workspace is constantly updated via the vehicle’s onboard sensors In particular, considering the sensing range of the vehicle, obstacle avoidance with any of the detected obstacles is guaranteed by the online generation of a collision-free trajectory tracking path, despite the model dynamic uncertainties and the presence of external disturbances representing ocean currents and waves Finally, realistic simulation studies verify the performance and efficiency of the proposed framework Note to Practitioners —This article was motivated by the problem of robust trajectory tracking for an autonomous underwater vehicle (AUV) operating in an uncertain environment where the knowledge of the operating workspace (eg, obstacle positions) is constantly updated online via the vehicle’s onboard sensors (eg, multibeam imaging sonars and laser-based vision systems) In addition, there may be other system limitations (eg, thruster saturation limits) and other operational constraints, induced by the need of various common underwater tasks (eg, a predefined vehicle speed limit for inspecting the seabed, and mosaicking), where it should also be considered into the control strategy However, based on the existing trajectory tracking control approaches for underwater robotics, there is a lack of an autonomous control scheme that provides a complete and credible control strategy that takes the aforementioned issues into consideration Based on this, we present a reliable control strategy that takes into account the aforementioned issues, along with dynamic uncertainties of the model and the presence of ocean currents In future research, we will extend the proposed methodology for multiple AUV performing collaborative inspection tasks in an uncertain environment

Journal ArticleDOI
Yan-Li Chen1, Guiqiang Bai1, Yin Zhan1, Hu Xinyu1, Jun Liu1 
TL;DR: In this article, the improved ant colony optimization-artificial potential field (ACO-APF) algorithm is proposed to improve path planning of USVs in dynamic environments, which is based on a grid map for both local and global path planning.
Abstract: Path planning is important to the efficiency and navigation safety of USV autonomous operation offshore. To improve path planning, this study proposes the improved ant colony optimization-artificial potential field (ACO-APF) algorithm, which is based on a grid map for both local and global path planning of USVs in dynamic environments. The improved ant colony optimization (ACO) mechanism is utilized to search for a globally optimal path from the starting point to the endpoint for a USV in a grid environment, and the improved artificial potential field (APF) algorithm is subsequently employed to avoid unknown obstacles during USV navigation. The primary contributions of this article are as follows: (1) this article proposes a new heuristic function, pheromone update rule, and dynamic pheromone volatilization factor to improve convergence and mitigate finding local optima with the traditional ant colony algorithm; (2) we propose an equipotential line outer tangent circle and redefine potential functions to eliminate goals unreachable by nearby obstacles (GNRONs) and local minimum problems, respectively; (3) to adapt the USV to a complex environment, this article proposes a dynamic early-warning step-size adjustment strategy in which the moving distance and safe obstacle avoidance range in each step are adjusted based on the complexity of the surrounding environment; (4) the improved ant colony optimization algorithm and artificial potential field algorithm are effectively combined to form the algorithm proposed in this article, which is verified as an effective solution for USV local and global path planning using a series of simulations. Finally, in contrast to most papers, we successfully perform field experiments to verify the feasibility and effectiveness of the proposed algorithm.

Journal ArticleDOI
TL;DR: In this article, a convolutional network is used to directly map noisy sensory observations to collision-free trajectories in a receding-horizon fashion, which reduces processing latency and increases robustness to noisy and incomplete perception.
Abstract: Quadrotors are agile. Unlike most other machines, they can traverse extremely complex environments at high speeds. To date, only expert human pilots have been able to fully exploit their capabilities. Autonomous operation with on-board sensing and computation has been limited to low speeds. State-of-the-art methods generally separate the navigation problem into subtasks: sensing, mapping, and planning. While this approach has proven successful at low speeds, the separation it builds upon can be problematic for high-speed navigation in cluttered environments. Indeed, the subtasks are executed sequentially, leading to increased processing latency and a compounding of errors through the pipeline. Here we propose an end-to-end approach that can autonomously fly quadrotors through complex natural and man-made environments at high speeds, with purely onboard sensing and computation. The key principle is to directly map noisy sensory observations to collision-free trajectories in a receding-horizon fashion. This direct mapping drastically reduces processing latency and increases robustness to noisy and incomplete perception. The sensorimotor mapping is performed by a convolutional network that is trained exclusively in simulation via privileged learning: imitating an expert with access to privileged information. By simulating realistic sensor noise, our approach achieves zero-shot transfer from simulation to challenging real-world environments that were never experienced during training: dense forests, snow-covered terrain, derailed trains, and collapsed buildings. Our work demonstrates that end-to-end policies trained in simulation enable high-speed autonomous flight through challenging environments, outperforming traditional obstacle avoidance pipelines.

Journal ArticleDOI
TL;DR: The proposed indexed-based scheme avoids the time-consuming policy exploration common in DRL scheduling approaches and makes effectual decisions with low complexity while adapting to time-variant vehicle mobility.
Abstract: This paper investigates computing resource scheduling for real-time applications in autonomous driving, such as localization and obstacle avoidance. In our considered scenario, autonomous vehicles periodically sense the environment, offload sensor data to an edge server for processing, and receive computing results from the server. Due to mobility and computing latency, a vehicle travels some distance in the duration between the instant of offloading its sensor data and the instant of receiving the computing result. Our objective is finding a scheduling scheme for the edge sever to minimize the above traveled distance of vehicles. The approach is to determine the processing order according to individual vehicle mobility and computing capability of the edge server. We formulate a restless multi-arm bandit (RMAB) problem, design a Whittle index based stochastic scheduling scheme, and determine the index using a deep reinforcement learning (DRL) method. The proposed scheduling scheme avoids the time-consuming policy exploration common in DRL scheduling approaches and makes effectual decisions with low complexity. Extensive simulation results demonstrate that the proposed indexed-based scheme can deliver computing results to the vehicles promptly while adapting to time-variant vehicle mobility.

Journal ArticleDOI
TL;DR: A coastal ship path planning model based on the optimized deep Q network (DQN) algorithm that can plan the optimal path in line with the actual navigation rules, and improve the safety, economy and autonomous decision-making ability of ship navigation is proposed.
Abstract: Path planning is a key issue in the field of coastal ships, and it is also the core foundation of ship intelligent development. In order to better realize the ship path planning in the process of navigation, this paper proposes a coastal ship path planning model based on the optimized deep Q network (DQN) algorithm. The model is mainly composed of environment status information and the DQN algorithm. The environment status information provides training space for the DQN algorithm and is quantified according to the actual navigation environment and international rules for collision avoidance at sea. The DQN algorithm mainly includes four components which are ship state space, action space, action exploration strategy and reward function. The traditional reward function of DQN may lead to the low learning efficiency and convergence speed of the model. This paper optimizes the traditional reward function from three aspects: (a) the potential energy reward of the target point to the ship is set; (b) the reward area is added near the target point; and (c) the danger area is added near the obstacle. Through the above optimized method, the ship can avoid obstacles to reach the target point faster, and the convergence speed of the model is accelerated. The traditional DQN algorithm, A* algorithm, BUG2 algorithm and artificial potential field (APF) algorithm are selected for experimental comparison, and the experimental data are analyzed from the path length, planning time, number of path corners. The experimental results show that the optimized DQN algorithm has better stability and convergence, and greatly reduces the calculation time. It can plan the optimal path in line with the actual navigation rules, and improve the safety, economy and autonomous decision-making ability of ship navigation.

Journal ArticleDOI
TL;DR: In this paper, a dynamic fusion path-finding algorithm (DFPA) based on Delaunay triangulation and improved A-star (A*) algorithm was designed to improve the efficiency of mobile robot path planning, where the concept of the grid was used to extract obstacle edges to provide obstacle avoidance strategies for robot pathfinding.
Abstract: Although many studies exist on mobile robot path planning, the disadvantages of complex algorithms and many path nodes in logistics warehouses and manufacturing workshops are obvious, mainly due to the inconsistency of map environment construction and pathfinding strategies In this study, to improve the efficiency of mobile robot path planning, the Delaunay triangulation algorithm was used to process complex obstacles and generate Voronoi points as pathfinding priority nodes The concept of the grid was used to extract obstacle edges to provide obstacle avoidance strategies for robot pathfinding Subsequently, the search for priority and regular path nodes used the improved A-star (A*) algorithm The dynamic fusion pathfinding algorithm (DFPA), based on Delaunay triangulation and improved A*, was designed, which realizes the path planning of mobile robots MATLAB 2016a was used as the simulation software, to firstly verify the correctness of the DFPA, and then to compare the algorithm with other methods The results show that under the experimental environment with the same start point, goal point, and number of obstacles, the map construction method and pathfinding strategy proposed in this paper reduce the planned path length of the mobile robot, the number of path nodes, and the cost of overall turn consumption, and increase the success rate of obtaining a path The new dynamic map construction method and pathfinding strategy have important reference significance for processing chaotic maps, promoting intelligent navigation, and site selection planning

Journal ArticleDOI
01 Apr 2021
TL;DR: This letter proposes a hybrid control methodology to achieve full body collision avoidance in anthropomorphic robot manipulators by introducing a Deep Reinforcement Learning approach trained ad hoc for performing obstacle avoidance, while achieving a reaching task in the operative space.
Abstract: This letter proposes a hybrid control methodology to achieve full body collision avoidance in anthropomorphic robot manipulators. The proposal improves classical motion planning algorithms by introducing a Deep Reinforcement Learning (DRL) approach trained ad hoc for performing obstacle avoidance, while achieving a reaching task in the operative space. More specifically, a switching mechanism is enabled whenever a condition of proximity to the obstacles is met, thus conferring to the dual-mode architecture a self-configuring capability in order to cope with objects unexpectedly invading the workspace. The proposal has been finally tested relying on a realistic robot manipulator simulated in a V-REP environment.

Journal ArticleDOI
31 Mar 2021
TL;DR: In this article, the authors propose Recovery RL, an algorithm that learns about constraint violating zones before policy learning and separates the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint violation is likely.
Abstract: Safety remains a central obstacle preventing widespread use of RL in the real world: learning new tasks in uncertain environments requires extensive exploration, but safety requires limiting exploration. We propose Recovery RL, an algorithm which navigates this tradeoff by (1) leveraging offline data to learn about constraint violating zones before policy learning and (2) separating the goals of improving task performance and constraint satisfaction across two policies: a task policy that only optimizes the task reward and a recovery policy that guides the agent to safety when constraint violation is likely. We evaluate Recovery RL on 6 simulation domains, including two contact-rich manipulation tasks and an image-based navigation task, and an image-based obstacle avoidance task on a physical robot. We compare Recovery RL to 5 prior safe RL methods which jointly optimize for task performance and safety via constrained optimization or reward shaping and find that Recovery RL outperforms the next best prior method across all domains. Results suggest that Recovery RL trades off constraint violations and task successes 2–20 times more efficiently in simulation domains and 3 times more efficiently in physical experiments. See https://tinyurl.com/rl-recovery for videos and supplementary material.

Journal ArticleDOI
TL;DR: A review on the snake motion and the body structure is provided, which outlines the biological foundation of all snake robots and the mechanical structure of snake robots, especially the structure of elemental snake modules are discussed.

Journal ArticleDOI
TL;DR: This paper introduces the human detection system for recognition of human gesture using a weighted dynamic time warping (DTW) with kinematic constraints, and proposes a feasible strategy to integrate these three aspects to achieve a conscious, safe, accurate, robust, and efficient navigation.
Abstract: Service robot navigation must take the humans into account explicitly so as to produce motion behaviors that reflect its social awareness. Generally, the navigation problems of mobile service robot can be summarized to three aspects: 1) human detection; 2) robot real-time localization; and 3) robot motion planning. The purpose of this paper is to provide a feasible strategy to integrate these three aspects to achieve a conscious, safe, accurate, robust, and efficient navigation. We first introduce the human detection system for recognition of human gesture using a weighted dynamic time warping (DTW) with kinematic constraints. Thus, by interpreting the human body language through gesture recognition, robot motion behaviors like heading to the assigned position or following people can be activated. Then, for the robot localization, a simultaneous localization and mapping (SLAM) method based on artificial and natural landmark recognition is employed to provide absolute position feedback in real time. For the motion planning, a novel quadrupole potential field (QPF) method is proposed to plan collision-free trajectories, adequately considering the nonholomic constraint of the mobile robot system. Then, a robust kinematic controller is designed for trajectory tracking to account for slip disturbances. Such a design automatically merges path finding, trajectory generation, and trajectory tracking in a closed-loop fashion, achieving simultaneous motion planning for obstacle avoidance and feedback stabilization to a desired position and orientation even in the presence of slippage. Finally, experiments prove the effectiveness and feasibility of the proposed strategy, showing a good navigation performance on mobile service robot.

Journal ArticleDOI
TL;DR: A novel human-in-the-loop control framework for a fully actuated lower limb exoskeleton with high degree-of-freedoms (DoFs), allowing users to walk without crutches or other external stabilization tools is proposed.
Abstract: Exoskeletons are increasingly used to assist humans in military, industry, and healthcare applications, thereby enabling individuals to gain increased strength and endurance. This article proposes a novel human-in-the-loop control framework for a fully actuated lower limb exoskeleton with high degree-of-freedoms (DoFs), allowing users to walk without crutches or other external stabilization tools. To imitate the natural lower limb motion of users, a novel barrier energy function is utilized for the design of the control strategy, where the human-robot manipulation space is reformulated as a human-voluntary and a robot-constrained region. The variations in the barrier energy function are based on the distance between the center of mass and zero moment point of the walking exoskeleton, thereby constraining the lower limb motion of the user to a compliant region around various desired trajectories. Based on varying regional functions, the proposed strategy is designed to control the exoskeleton to follow appropriate ergonomic trajectories. For such a purpose, an adaptive controller is exploited considering the functions of the human effort and the robot's capabilities simultaneously, and a smooth motion transition can be achieved between the human and robot regions. Finally, physical experiments are conducted on a ten-DoFs walking exoskeleton to validate the stability and robustness of the proposed control framework with subjects performing flat walking, turning, and obstacle avoidance movements.

Proceedings ArticleDOI
25 May 2021
TL;DR: In this article, a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs) was proposed to guarantee system safety and accomplishes optimal performance via MPC.
Abstract: The optimal performance of robotic systems is usually achieved near the limit of state and input bounds. Model predictive control (MPC) is a prevalent strategy to handle these operational constraints, however, safety still remains an open challenge for MPC as it needs to guarantee that the system stays within an invariant set. In order to obtain safe optimal performance in the context of set invariance, we present a safety-critical model predictive control strategy utilizing discrete-time control barrier functions (CBFs), which guarantees system safety and accomplishes optimal performance via model predictive control. We analyze the feasibility and the stability properties of our control design. We verify the properties of our method on a 2D double integrator model for obstacle avoidance. We also validate the algorithm numerically using a competitive car racing example, where the ego car is able to overtake other racing cars.

Journal ArticleDOI
TL;DR: A scheme that facilitates the autonomous navigation of UAVs in the indoor corridors of a building using deep-neural-networks-based processing of images using genetic algorithms and state-of-the-art ImageNet models is introduced.
Abstract: The applications of unmanned aerial vehicles (UAVs) in military, intelligent transportation, agriculture, rescue operations, natural environment mapping, and many other allied domains has increased exponentially during the past few years. Some of the use cases of their applications range from aerial surveillance, data retrieval to their use in real-time communicative networks. Though UAVs were traditionally used only outdoors, many of its indoor applications like for rescue operations, inventory tracking in warehouses, etc., have recently emerged and these use cases are being actively explored. One of the major challenges for indoor drone applications is navigation and obstacle avoidance. Due to indoor operations, the global positioning system fails in accurate localization and navigation. To address this issue, we introduce a scheme that facilitates the autonomous navigation of UAVs (which have an onboard camera) in the indoor corridors of a building using deep-neural-networks-based processing of images. For a deep neural network, the selection of a good combination of hyperparameters for a better prediction is a complicated task. In this article, the hyperparameters tuning of a convolutional neural network is achieved by using genetic algorithms. The proposed architecture (DCNN-GA) is compared with state-of-the-art ImageNet models. The experimental results show the minimum loss and high performance of the proposed algorithm.

Journal ArticleDOI
TL;DR: The results of simulation indicated that the improved PSO can effectively avoid the precocity of particles and enhance the optimization capability and stability of the PSO; the improved APF would not be restricted by local minimum point and achieve dynamic obstacle avoidance under the constraints of global optimization path.

Journal ArticleDOI
TL;DR: Modified SMOA takes less time and effort to generate an optimal collision-free path as compared to other NISI metaheuristic approaches such as PSO, FA, SFLA and ABC.

Journal ArticleDOI
Mateusz Gil1
TL;DR: In this article, an improved concept of the CADCA (Collision Avoidance Dynamic Critical Area) is introduced for the case of ship allision, which can be used to appoint a position of no-return in a close-quarters situation, so as to determine the time and distance of the last-minute maneuver.

Journal ArticleDOI
TL;DR: In this article, a path optimization problem description for welding robot path optimization is presented, and an intelligent path optimization algorithm is introduced to realize effective robot path planning and obstacle avoidance strategies.

Journal ArticleDOI
TL;DR: In this paper, a differential dynamic programming (DDP) algorithm for solving discrete-time finite-horizon optimal control problems with inequality constraints was proposed, which can handle nonlinear state and input inequality constraints without a discernible increase in its computational complexity relative to the unconstrained case.
Abstract: This brief introduces a novel differential dynamic programming (DDP) algorithm for solving discrete-time finite-horizon optimal control problems with inequality constraints. Two variants, namely feasible- and infeasible-IPDDP algorithms, are developed using a primal–dual interior-point methodology, and their local quadratic convergence properties are characterized. We show that the stationary points of the algorithms are the perturbed KKT points, and thus can be moved arbitrarily close to a locally optimal solution. Being free from the burden of the active-set methods, it can handle nonlinear state and input inequality constraints without a discernible increase in its computational complexity relative to the unconstrained case. The performance of the proposed algorithms is demonstrated using numerical experiments on three different problems: control-limited inverted pendulum, car-parking, and unicycle motion control and obstacle avoidance.

Journal ArticleDOI
TL;DR: An improved Otsu algorithm is proposed to accurately identify obstacles and Kalman filtering is also introduced to estimate dynamic obstacles in the complex operation environment of the pipeline inspection.

Journal ArticleDOI
TL;DR: In this article, an improved Ant Colony Optimization with Fuzzy Logic (ACO-FL) is proposed to deal with local path planning for obstacle avoidance by taking into account wind, current, wave and dynamic obstacles.