Automatic Waypoint Generation to Improve Robot Navigation Through Narrow Spaces

Carrying out the task of the exploration of a scene by an autonomous robot entails a set of complex skills, such as the ability to create and update a representation of the scene, the knowledge of the regions of the scene which are yet unexplored, the ability to estimate the most efficient point of view from the perspective of an explorer agent and, finally, the ability to physically move the system to the selected Next Best View (NBV). This paper proposes an autonomous exploration system that makes use of a dual OcTree representation to encode the regions in the scene which are occupied, free, and unknown. The NBV is estimated through a discrete approach that samples and evaluates a set of view hypotheses that are created by a conditioned random process which ensures that the views have some chance of adding novel information to the scene. The algorithm uses ray-casting defined according to the characteristics of the RGB-D sensor, and a mechanism that sorts the voxels to be tested in a way that considerably speeds up the assessment. The sampled view that is estimated to provide the largest amount of novel information is selected, and the system moves to that location, where a new exploration step begins. The exploration session is terminated when there are no more unknown regions in the scene or when those that exist cannot be observed by the system. The experimental setup consisted of a robotic manipulator with an RGB-D sensor assembled on its end-effector, all managed by a Robot Operating System (ROS) based architecture. The manipulator provides movement, while the sensor collects information about the scene. Experimental results span over three test scenarios designed to evaluate the performance of the proposed system. In particular, the exploration performance of the proposed system is compared against that of human subjects. Results show that the proposed approach is able to carry out the exploration of a scene, even when it starts from scratch, building up knowledge as the exploration progresses. Furthermore, in these experiments, the system was able to complete the exploration of the scene in less time when compared to human subjects.

Section: Discussionmentioning

confidence: 99%

Autonomous Scene Exploration for Robotics: A Conditional Random View-Sampling and Evaluation Using a Voxel-Sorting Mechanism for Efficient Ray Casting

Santos

Oliveira

Arrais

et al. 2020

“…Figure 1 presents several types of data provided by the Robot-at-Home dataset. There are some multi-modal fusion works discussed based on the Robot-at-Home dataset, such as multi-layer semantic structure analysis using RGB-D information combined with LIDAR data [ 109 ], visual odometry with the assistance of depth data [ 110 ], and path planning by the combination of depth data and LiDAR data [ 111 ], etc.…”

Section: Multi-modal Datasetsmentioning

confidence: 99%

An Outline of Multi-Sensor Fusion Methods for Mobile Agents Indoor Navigation

Yang

Zhang

et al. 2021

Indoor autonomous navigation refers to the perception and exploration abilities of mobile agents in unknown indoor environments with the help of various sensors. It is the basic and one of the most important functions of mobile agents. In spite of the high performance of the single-sensor navigation method, multi-sensor fusion methods still potentially improve the perception and navigation abilities of mobile agents. This work summarizes the multi-sensor fusion methods for mobile agents’ navigation by: (1) analyzing and comparing the advantages and disadvantages of a single sensor in the task of navigation; (2) introducing the mainstream technologies of multi-sensor fusion methods, including various combinations of sensors and several widely recognized multi-modal sensor datasets. Finally, we discuss the possible technique trends of multi-sensor fusion methods, especially its technique challenges in practical navigation environments.

“…Driven by the labor shortage, the need for safe production processes, and people's demand for a comfortable life, automation technology has gradually penetrated every aspect of production and life in recent decades [1,2]. For example, automated guided vehicles (AGV) have been broadly applied to the handling of heavy objects or large devices in production environments [3], multi-axis CNC machines have been extensively used to machine parts with sculptured surfaces in the fields of machinofacture and aerospace [4], robots have been developed for welding, spraying and assembling in smart factories [5], firefighting robots have come into service in order to reduce the risks that human firefighters face [6], the Roomba promises its customers "effortless cleaning" or robot vacuums allow owners to "clean your floors without lifting a finger" [7], and feeding assistive robots have been proposed to help older people and people with disabilities in their daily life [8].…”

Section: Introductionmentioning

confidence: 99%

“…Despite the abundant support of advanced technologies, many problems remain in achieving fully safe autonomous driving [2]. One of the problems to be solved is how to achieve the robustness and stability of motion control, since motion controllers have a core role in generating action commands to stabilize to the reference path or trajectory in the presence of modeling error and other forms of uncertainty [18].…”

Section: Introductionmentioning

confidence: 99%

HFO-LADRC Lateral Motion Controller for Autonomous Road Sweeper

Zeng

Liu

et al. 2020

How to make a controller robust and stable to reject the disturbance of uncertainty is an inevitable challenge. Aiming at addressing the lateral control problem for an autonomous road sweeper, a heading-error-based first order linear active disturbance rejective controller (HFO-LADRC) is proposed in this paper. To eliminate the lateral error and the heading error at the same time, a new model, called the heading-error-based model, is proposed for lateral motion, and the Lyapunov function was employed to explore the convergence ability of the heading error and lateral error. Since the heading-error-based model is first order, the ADRC is designed as first order and linear, and each module of the HFO-LADRC has been devised in detail. To ensure solution accuracy, the fourth order Runge–Kutta method was adopted as the differential system solver, and a typical ring scenario and a double lane-changing scenario were designed referencing the standard. Considering the obvious influence, wheelbase uncertainty, steering ratio uncertainty and Gaussian white noise disturbance were taken into account for the tests. The results illustrate that, in the case of both wheelbase uncertainty and steer ratio uncertainty, the HFO-LADRC has strong robustness and stability compared with a typical pure pursuit controller and classical SO-LADRC.