scispace - formally typeset
Search or ask a question
Topic

Obstacle

About: Obstacle is a research topic. Over the lifetime, 9517 publications have been published within this topic receiving 94760 citations. The topic is also known as: impediment & barrier.


Papers
More filters
01 Sep 1995
TL;DR: In this paper, the authors present a new approach for planning a robot's trajectory that avoids static and moving obstacles and minimizes motion time, subject to robot dynamics and actuator constraints.
Abstract: This thesis presents a new approach for planning a robot's trajectory that avoids static and moving obstacles and minimizes motion time, subject to robot dynamics and actuator constraints. This approach consists of first computing a coarse trajectory that avoids the obstacles and satisfies an approximation of the actuator constraints. Then this trajectory is used as the initial guess of a dynamic optimization that satisfies obstacle avoidance, robot dynamics and the true actuator limits. The first step of the approach is based on the concept of Velocity Obstacle (VO) that defines, at every instant in time, the set of colliding velocities between the robot and the obstacles. The VO set is computed using the relative velocity between the robot and each obstacle, and is instrumental in determining the set of robot velocities avoiding all obstacles and satisfying approximate system dynamics and actuator limits. Within this set, the best avoidance maneuver is chosen heuristically so that the trajectory resulting from the sequence of maneuvers reaches the goal and minimizes motion time. The second step of the approach consists of refining the trajectory with a dynamic optimization that minimizes motion time, subject to the true robot's dynamics, actuator constraints, and time varying obstacle constraints. The dynamic optimization is based on Pontryagin's Minimum Principle and uses a gradient descent method. These two steps lead to the implementation of a powerful and flexible planner that combines the advantages of heuristics with those of dynamic optimization. Heuristics in fact, captures the non-analytic aspects of motion planning, such as sequence of obstacle avoidance, conservative or aggressive maneuvers, and so on, thus characterizing the global structure of the trajectory. Dynamic optimization on the other hand, ensures feasibility and optimality of the trajectory thus guaranteeing its local correctness. This approach is demonstrated for planning the motions of an automated vehicle in an Intelligent Vehicle Highway System (IVHS) scenario, and of an articulated robot moving in a dynamic environment. This motion planner is suitable to a wide range of applications. The Velocity Obstacle method is very fast and, although approximate, it can be used for real time planning. The Dynamic Optimization is computationally intensive, but yields optimal solutions, which can be used when off-line planning is acceptable.

26 citations

Proceedings ArticleDOI
22 Apr 1996
TL;DR: This method is applied to collision-free motion planning for a mobile robot in a dynamic and unknown environment with several moving and stationary obstacles and is effective for moving obstacle avoidance.
Abstract: This paper proposes a new motion planning method of a mobile robot avoiding moving obstacles. To avoid moving obstacles, the trajectories of the obstacles are predicted using a stochastic model of obstacle motion. The obstacle motion is modeled as a random walk process. The method plans robot motion by the unit of view-time and view-period. View-time is defined as the time instant at which the robot senses the obstacle position and velocity. View-period is defined as the time interval during which the robot performs sensing, predicting and planning for collision-free motion. From the position and velocity at a view-time, we predict the future position of the obstacle. The random walk process model of obstacle motion is used to calculate the probability density that the predicted position is reached during the view-period. From the probability density function of the predicted position, the probability that a position can be swept by the obstacle during the view-period is calculated. Then artificial potential is assigned at every position by considering the probability. The force induced by the artificial potential field repels the robot away from the probable obstacle trajectory. This method is a look ahead scheme, and effective for moving obstacle avoidance. This method is applied to collision-free motion planning for a mobile robot in a dynamic and unknown environment with several moving and stationary obstacles.

26 citations

Journal ArticleDOI
TL;DR: A novel approach to the autonomous navigation of a small UAV in tree plantations only using a single camera and a machine learning model, Faster Region-based Convolutional Neural Network (Faster R-CNN), was trained for tree trunk detection.
Abstract: In recent years, Unmanned Aerial Vehicles (UAVs) are widely utilized in precision agriculture, such as tree plantations. Due to limited intelligence, these UAVs can only operate at high altitudes, leading to the use of expensive and heavy sensors for obtaining important health information of the plants. To fly at low altitudes, these UAVs must possess the capability of obstacle avoidance to prevent crashes. However, most current obstacle avoidance systems with active sensors are not applicable to small aerial vehicles due to the cost, weight, and power consumption constraints. To this end, this paper presents a novel approach to the autonomous navigation of a small UAV in tree plantations only using a single camera. As the monocular vision does not provide depth information, a machine learning model, Faster Region-based Convolutional Neural Network (Faster R-CNN), was trained for the tree trunk detection. A control strategy was implemented to avoid the collision with trees. The detection model uses image heights of detected trees to indicate their distances from the UAV and image widths between trees to find the widest obstacle-free space. The control strategy allows the UAV to navigate until any approaching obstacle is detected and to turn to the safest area before continuing its flight. This paper demonstrates the feasibility and performance of the proposed algorithms by carrying out 11 flight tests in real tree plantation environments at two different locations, one of which is a new place. All the successful results indicate that the proposed method is accurate and robust for autonomous navigation in tree plantations.

26 citations

Journal ArticleDOI
TL;DR: The limited sensing field of view and non-holonomic kinematic constraints of the mobile robot are incorporated into the proposed maximum-speed aware velocity obstacle (MVO) algorithm, for a mobile robot to avoid one or multiple high-speed obstacles.
Abstract: It is challenging for a mobile robot to avoid moving obstacles in dynamic environments. Traditional velocity obstacle methods do not fully consider the obstacles moving with the speeds larger than the maximum speed of the robot. In this article, a new obstacle avoidance method, named the maximum-speed aware velocity obstacle (MVO) algorithm, is proposed for a mobile robot to avoid one or multiple high-speed obstacles. The proposed algorithm expands the velocity obstacle region into two parts, where one of the parts foresees collisions beyond the time horizon to ensure the feasible solutions of the current and the next control step. In practical applications, the perception capability of the robot is generally limited, and a non-holonomic robot can’t move into any direction due to its kinematic constraints. In this article, the limited sensing field of view and non-holonomic kinematic constraints of the mobile robot are incorporated into the proposed MVO method. Moreover, continuity, safety, and computational complexity of the MVO approach are analyzed and presented. Extensive simulations and physical experiments are conducted to verify the efficacy of the MVO method, where a quadrotor and a differential-drive robot are used to perform dynamic obstacle avoidance.

26 citations

01 Jan 2013
TL;DR: A multigrid algorithm based on the full approximate scheme (FAS) for solving the membrane constrained obstacle problems and the minimal surface obstacle problems in the formulations of HJB equations is proposed.
Abstract: Obstacle problems can be posed as elliptic variational inequalities, complementarity inequalities and Hamilton-Jacobi-Bellman (HJB) partial differential equations (PDEs). In this paper, we propose a multigrid algorithm based on the full approximate scheme (FAS) for solving the membrane constrained obstacle problems and the minimal surface obstacle problems in the formulations of HJB equations. A special coarse grid operator is proposed based on the Galerkin operator for the membrane constrained obstacle problem in this paper. Comparing with standard FAS with the direct discretization coarse grid operator, the FAS with the proposed operator converges faster. Due to the nonlinear property of the minimal surface operator, the Galerkin operator for the minimal surface obstacle problem is not accurate. We introduce the direct discretization operator for the minimal surface obstacle problem. A special prolongation operator based on the bilinear interpolation is proposed to interpolate functions from the coarse grid to the fine grid. At the boundary between the active set and inactive set, the proposed prolongation operator can capture the active grid points and put accurate values at these points. We will demonstrate the fast convergence of the proposed multigrid method for solving obstacle problems by comparing with other multigrid methods.

26 citations


Network Information
Related Topics (5)
Nonlinear system
208.1K papers, 4M citations
79% related
Artificial neural network
207K papers, 4.5M citations
78% related
Fuzzy logic
151.2K papers, 2.3M citations
77% related
Software
130.5K papers, 2M citations
77% related
Optimization problem
96.4K papers, 2.1M citations
76% related
Performance
Metrics
No. of papers in the topic in previous years
YearPapers
20241
20231,483
20223,389
2021407
2020817
2019873