The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
Autonomous robot navigation through unknown, cluttered environments at high-speeds is still an open problem. Quadrotor platforms with this capability have only begun to emerge with the advancements in light-weight, small form factor sensing and computing. Many of the existing platforms, however, require excessive computation time to perform collision avoidance, which ultimately limits the vehicle's...
For robots to be a part of our daily life, they need to be able to navigate among crowds not only safely but also in a socially compliant fashion. This is a challenging problem because humans tend to navigate by implicitly cooperating with one another to avoid collisions, while heading toward their respective destinations. Previous approaches have used handcrafted functions based on proximity to model...
Deep reinforcement learning is rapidly gaining attention due to recent successes in a variety of problems. The combination of deep learning and reinforcement learning allows for a generic learning process that does not consider specific knowledge of the task. However, learning from scratch becomes more difficult when tasks involve long trajectories with delayed rewards. The chances of finding the...
Collision-free is one of the major safety concerns for maritime traffic management. To analyze the collision data and understand the cause of the collision can contribute the improvement of the maritime traffic safety and management. However, the real collisions is not always available to analyze. Based on a massive AIS trajectory data collected, we focus on mining the ships' movement behaviors those...
In this paper we propose an enhancement to our previous Conditional Random Field (CRF) based map matching algorithm in order to make the map matched trajectory smoother and more feasible. The existing algorithm uses one feature, which is the distance with the input coordinate, and has the problem of non-smooth output trajectory. In this work we propose adding a new semantic layer to the map model...
Affective (emotional) responses contribute to student engagement and, ultimately, to the decision to persist or withdraw from Computer Science as a discipline of study. We investigate affective response as a factor contributing to engagement and professional identity formation during the university-to-work transition, as supported during a senior capstone project experience. By conducting qualitative...
A solution for precise indoor localization is sought by the robot navigation scientific community. There are many approaches to solve this problem, including sensor fusion: inertial sensors, cameras, lasers and signal strength-based methods (Wi-Fi). This paper presents an approach using a single camera embedded on the robot, pointing to the floor. To validate this method, an application using an electric...
Robots based on vision guidance are very important to the future of vehicle navigation. They have the ability to navigate through a predetermined track and avoid obstacles. They operate remotely with a central computer tracking and guiding them. This allows for communication between robots. This can be used to implement traffic based navigation. Where routes can be recalculated depending on traffic...
This paper describes an optimal motion control for mobile robots with differential drive. We propose a novel method called Particle Filter Model Predictive Equilibrium Point Control (PF-MPEPC) that implements robot navigation with obstacle avoidance in a structured environment. This control evaluates the near future behaviour continuously to generate an optimal trajectory that is safe and smooth.
We consider the problem of path planning in an initially unknown environment where a robot does not have an a priori map of its environment but has access to prior information accumulated by itself from navigation in similar but not identical environments. To address the navigation problem, we propose a novel, machine learning-based algorithm called Semi-Markov Decision Process with Unawareness and...
This paper proposes a novel curve smoothing method for path planners with curvature constraint in which the positions of the nodes from the planner are updated. For a smooth trajectory, we adopt Bezier curve where the optimal positions of its control points are found in order to satisfy curvature constraint. These curves are calculated in a piece-wise manner and connected to obtain the whole path...
Follow the Gap Method (FGM) is an obstacle avoidance method which uses gap arrays. This method recursively directs robot to the goal state while avoiding the obstacles through the safest gap. Since FGM is a geometric method, it does not consider the robot dynamics. For this reason, oscillations or collisions due to robot dynamics is possible. On the other hand, FGM calculates a desired heading angle...
Recent years have seen a fast growth in the number of applications of Machine Learning algorithms from Computer Science to Robotics. Nevertheless, while most such attempts were successful in maximizing robot performance after a long learning phase, to our knowledge none of them explicitly takes into account the budget in the algorithm evaluation: e.g. budget limitation on the learning duration or...
The Automatic Identification System (AIS) is an automatic tracking system which has been widely applied in the fields of intelligent transportation systems, e.g., collision avoidance, navigation, maritime supervision and management. Compare with other positioning systems, e.g., very high frequency (VHF) and radar, AIS can conquer the human errors and it is almost not affected by the external environment...
The problem of having a multi-agent nonholonomic systems achieve a desired mission in a multi-threat prone environment is addressed in this paper. In such hostile environment, the ability to reach a target, keep formation and evade a threat is crucial. This paper proposes a behavioral control algorithm that makes the multi-agent system operates by switching through different navigation algorithms...
This paper presents a novel method of sonar vision, called side sonar vision (SSV), to navigate mobile robots in a known environment. It adopts Omni-directional images and divides surrounding sonar vision into three parts: front, right and left sides. These sides are under continuous scrutiny of individual agents. SSV analyses data of each side, separately, and produces two key parameters: angle and...
This work details Visio and path following control system of a non-holonomic Two-Wheeled Mobile Robot. We present a control algorithm based on two control blocs. A speed inner loop regulation is first studied based on state feedback theorem to ensure stability of the structure. A second outer loop regulation is proposed to enable the robot navigate along a desired destination presented as a set of...
Manifold AUV uses are viewed on the basis of the idea of ocean physical fields. An example is the problem of trajectory survey of the seabed field and navigation according to the bathymetric map. Application of known methods to the problems of AUV motion control runs into certain difficulties with regard to investigation of poorly known ocean areas. In this case representation of the field map does...
We propose a method for navigation of autonomous underwater vehicle based on visual odometry with regard to the conditions of the local maneuvers. The method is based on the SLAM-algorithm for stereo images and recognition algorithm for re-visited places. The operation of the algorithm for places recognition is based on using of virtual network for coordinate binding, which is constructed at the time...
Traditional coverage path planners create lawnmower-type paths in the operating area completely ignoring the uncertainty in the vehicle's position. However, in the presence of significant uncertainty in localization estimates, one can no longer guarantee that the vehicle will cover all the area according to plan. Aiming to bridge this gap, we present a coverage path planning technique for search operations...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.