Event based cameras are a new passive sensing modality with number of benefits over traditional cameras, including extremely low latency, asynchronous data acquisition, high dynamic range and very power consumption. There has been lot recent interest development in applying algorithms to use the events perform variety 3D perception tasks, such as feature tracking, visual odometry, stereo depth estimation. However, there currently lacks wealth labeled that exists for be used both testing...

This letter considers the problem of reducing uncertainty about a physical process interest by designing sensing trajectories for team robots. active information gathering has applications in environmental monitoring, search and rescue, security surveillance. Our previous work developed search-based planning method which prunes uninformative from space while providing suboptimality guarantees decentralizes across multiple robots via coordinate descent. The novelty this is to demonstrate...

Abstract This paper addresses the problem of autonomous cooperative localization, grasping and delivering colored ferrous objects by a team unmanned aerial vehicles (UAVs). In proposed scenario, UAVs is required to maximize reward collecting them predefined location. task consists several subtasks such as coverage path planning, object detection state estimation, UAV self‐localization, precise motion control, trajectory tracking, dropping, decentralized coordination. The failure recovery...

Autonomous Micro Aerial Vehicles (MAVs) have the potential to assist in real-life tasks involving grasping and transportation, but not before solving several difficult research challenges. In this work, we address design, control, estimation, planning problems for cooperative localization, grasping, transportation of objects challenging outdoor scenarios. We demonstrate an autonomous team MAVs able plan safe trajectories manipulation ferrous objects, while guaranteeing interrobot collision...

Mobile manipulators have the potential to revolutionize modern agriculture, logistics and manufacturing. In this work, we present design of a ground-based mobile manipulator for automated structure assembly. The proposed system is capable autonomous localization, grasping, transportation deployment construction material in semi-structured environment. Special effort was put into making invariant lighting changes, not reliant on external positioning systems. Therefore, presented...

Algorithms for fixed-wing unmanned aerial systems (UAS) must integrate on-board sensor capabilities and vehicle maneuver constraints to reliably satisfy the objectives of persistent surveillance, path planning, trajectory management. In many cases, characteristic dimensions fields view are comparable with turning radius UAS platform. Consequently, when persistent, full area, time-critical coverage is required number assets limited, complexity planning increased, as turn becomes or exceeds...

We autonomously pour from unknown symmetric containers found in a typical wet laboratory for the development of robot-assisted, rapid experiment preparation system. The robot estimates pouring container geometry, then leverages simulated pours as priors given fluid to precisely and quickly single attempt. is detected transparent receiving by combining weight vision. change volume receiver function geometry container, angle, rate. To determine volumetric flow rate, profile maximum containable...

We are interested in the multiple robot surveillance problem where robots must allocate waypoints to be visited among themselves and plan paths through different while avoiding obstacles. Furthermore, allocated specific times reach their respective goal locations as a result they have decide which visit waypoints. Such has challenge of computing allocation across robots, ordering for these dynamical feasibility between present an algorithm that runs series graph searches solve provide...

Applications of safety, security, and rescue in robotics, such as multi-robot target tracking, involve the execution information acquisition tasks by teams mobile robots. However, failure-prone or adversarial environments, robots get attacked, their communication channels jammed, sensors may fail, resulting withdrawal from collective task, consequently inability remaining active to coordinate with each other. As a result, traditional design paradigms become insufficient and, contrast,...

Time optimal path planning and trajectory management algorithms for air vehicles with limited on-board computing resources require an efficient approach to satisfy flight dynamic constraints needed guarantee paths are feasible. B-spline curves enable compact definition of feasible airplane trajectories that suited real-time computation. The design a algorithm multi-agent persistent surveillance application is described. proposed solution post-processes the output point-by-point planner...

Robotic pouring is an important step in improving the safety, productivity and repeatability biotechnology industry generally increasing effectiveness of robotics human based environments. In this work we present a method to autonomously dispense precise amount fluid using only visual feedback without precision instruments such as pipettes, syringes or pourers. We model circular rectangular container geometries. prove that for square containers can control flow by observing height receiving...

Autonomous flight through unknown environments in the presence of obstacles is a challenging problem for micro aerial vehicles (MAVs). A majority current state-of-art research assumes as opaque objects that can be easily sensed by optical sensors such cameras or LiDARs. However indoor with glass walls and windows, scenarios smoke dust, robots (even birds) have difficult time navigating space.In this paper, we present design new class achieves autonomous navigation are robust to collisions....

Robots are ideally suited to performing simple tasks in dangerous environments. In this letter, we address the use of robots for inspection nuclear reactors which may be contaminated by radiation. The geometry a reactor vessel is three-dimensional with significant clutter. Accordingly, propose small-scale, flying that able localize themselves and autonomously navigate around obstacles. Because constraints on size, rely cameras best low power lightweight sensors. However, perform poorly...

This paper presents an automated robotic system for generating semantic maps of inventory in retail environments. In settings, are labeled stores where each discrete section shelving is assigned a department label describing the types products on that shelf. Starting from metric map store, robot autonomously extracts shelf boundaries, generates distance-optimal tour store to view every shelf, and follows while avoiding unmapped clutter moving people. The creates point cloud using data...

We consider a scenario where team of robots with heterogeneous sensors must track set targets or hazards which may induce sensory failures on the robots. In particular, likelihood depends proximity between and propose control framework that explicitly addresses competing objectives tracking quality maximization sensor preservation (which impacts future generated target estimates). Our consists risk-aware component—which accounts for risk suffering failures, an adaptive balances...

This paper presents an automated system for generating a semantic map of inventory in retail environment. Developing this involves assigning department label to each discrete section shelving. We use priori information boost data from laser and camera sensors object recognition labeling. introduce soft dynamic programming algorithm point cloud segmentation. The primary contribution work is the integration multiple systems including path planning navigation subsystem mapping system. also...

Unmanned Aerial Vecicles (UAVs) in civil and military applications are becoming increasingly popular. Various platform types have already shown their great potential missions that require rapid surveillance capabilities or logistic support. Large scale incidents the deployment of several platforms with various capabilities. In this case, coordinated use will lead to more efficient given resources. Problems resolve resemble known optimization problems from field vehicle routing scheduling....

In our culture, crime is a major problem that affects everyone. Many crimes take place every day. The dataset utilized in this study includes data on each year's date and rate. This initiative mainly focuses the rate related to robberies. Using historical data, linear regression technique used forecast future rates. programmer accepts as input outputs matching percentage of

In this work, we address the design, estimation, planning, control, and mapping problems to allow a small scale quadrotor autonomously inspect interior of Containment Vessel (CV) test fixture, using on-board lighting, computation sensing. We demonstrate fully autonomous, 160 cm tip-to-tip, 236 gram Micro Aerial Vehicle (MAV) performing complex flight mission inside dark fixture that was built from model CV. The proposed solution opens up new ways nuclear power plants has potential support...

Scalable training data generation is a critical problem in deep learning. We propose PennSyn2Real - photo-realistic synthetic dataset consisting of more than 100 000 4K images 20 types micro aerial vehicles (MAVs). The can be used to generate arbitrary numbers for high-level computer vision tasks such as MAV detection and classification. Our framework bootstraps chroma-keying, mature cinematography technique, with motion tracking system providing artifact-free curated annotated images....

We consider planar navigation for a polygonal, holonomic robot in an obstacle-filled environment SE(2). To determine the free space, we first represent obstacles as point clouds configuration space (C). A point-wise Minkowski sum of and obstacle points is then calculated C using convex hull varying configurations. Using graph search, obtain seed path, which used our novel method to compute overlapping regions consecutive path chords. The resulting provide collision-free useful finding...

Autonomous mobile robots have the potential to execute missions that are either too complex or dangerous for humans. In this paper, we address design and deployment of an autonomous ground vehicle equipped with a robotic arm urban firefighting scenarios. We describe hardware algorithm designs navigation, planning, fire source identification abatement in unstructured Our approach employs on-board sensors navigation thermal camera information identification. A custom electro–mechanical pump is...

The task addressed in this article is the localization of an unknown number targets using a mobile robot equipped with visual sensor. estimation and their locations done recursive Bayesian filter over random finite sets (RFSs), position assumed to be known. We present computationally tractable control law whereby follows gradient mutual information between target detections. method verified through real-world experimental trials, reliably detecting multiple ignoring clutter obstacles.

A planar path planner for a persistent surveillance application in the presence of static obstacles is developed team homogeneous unmanned aircraft systems (UAS). The role to provide complete coverage (sensor data or image acquisition) user designated area within specified period. two stage chosen so that vehicle maneuver constraints can be satisfied computationally efficient manner. solution uses combination graph search and B-spline parametric curve construction. rationale selection...