Intelligent unmanned autonomous systems are some of the most important applications of artificial intelligence (AI). The development of such systems can significantly promote innovation in AI technologies. This paper introduces the trends in the development of intelligent unmanned autonomous systems by summarizing the main achievements in each technological platform. Furthermore, we classify the relevant technologies into seven areas, including AI technologies, unmanned vehicles, unmanned aerial vehicles, service robots, space robots, marine robots, and unmanned workshops/intelligent plants. Current trends and developments in each area are introduced.

/pdf/current-trends-in-the-development-of-intelligent-unmanned-jstjmm420w.pdf

Current trends in the development of intelligent unmanned autonomous systems

3D scene modeling has long been a fundamental problem in computer graphics and computer vision. With the popularity of consumer-level RGB-D cameras, there is a growing interest in digitizing real-world indoor 3D scenes. However, modeling indoor 3D scenes remains a challenging problem because of the complex structure of interior objects and poor quality of RGB-D data acquired by consumer-level sensors. Various methods have been proposed to tackle these challenges. In this survey, we provide an overview of recent advances in indoor scene modeling techniques, as well as public datasets and code libraries which can facilitate experiments and evaluation.

/pdf/3d-indoor-scene-modeling-from-rgb-d-data-a-survey-17n9yebdw9.pdf

3D indoor scene modeling from RGB-D data: a survey

A visual tracking system is essential as a basis for visual servoing, autonomous navigation, path planning, robot-human interaction and other robotic functions. To execute various tasks in diverse and ever-changing environments, a mobile robot requires high levels of robustness, precision, environmental adaptability and real-time performance of the visual tracking system. In keeping with the application characteristics of our amphibious spherical robot, which was proposed for flexible and economical underwater exploration in 2012, an improved RGB-D visual tracking algorithm is proposed and implemented. Given the limited power source and computational capabilities of mobile robots, compressive tracking (CT), which is the effective and efficient algorithm that was proposed in 2012, was selected as the basis of the proposed algorithm to process colour images. A Kalman filter with a second-order motion model was implemented to predict the state of the target and select candidate patches or samples for the CT tracker. In addition, a variance ratio features shift (VR-V) tracker with a Kalman estimation mechanism was used to process depth images. Using a feedback strategy, the depth tracking results were used to assist the CT tracker in updating classifier parameters at an adaptive rate. In this way, most of the deficiencies of CT, including drift and poor robustness to occlusion and high-speed target motion, were partly solved. To evaluate the proposed algorithm, a Microsoft Kinect sensor, which combines colour and infrared depth cameras, was adopted for use in a prototype of the robotic tracking system. The experimental results with various image sequences demonstrated the effectiveness, robustness and real-time performance of the tracking system.

http://www.guolab.org/Papers/2015/SENSORS2015.pdf

A Kinect-Based Real-Time Compressive Tracking Prototype System for Amphibious Spherical Robots

Autonomous mobile robots are required to move throughout map the environment, locate themselves, and plan paths between positions. Vision stands out among the other senses for its richness and practicality. Even though there are well-established autonomous navigation solutions, as far as we can tell, no complete autonomous navigation system that is solely based on vision and that is suitable for dynamic indoor environments has fully succeeded. This article presents a systematic literature review of methods and techniques used to solve the complete autonomous navigation problem or its parts: localization, mapping, path planning, and locomotion. The focus of this review lays on vision-based methods for indoor environments and ground robots. A total of 121 studies were considered, comprising methods, conceptual models, and other literature reviews published between 2000 and 2017. To the best of our knowledge, this is the first systematic review about vision-based autonomous navigation suitable for dynamic indoor environments. It addresses navigation methods, autonomous navigation requirements, vision benefits, methods testing, and implementations validation. The results of this review show a deficiency in testing and validation of presented methods, poor requirements specification, and a lack of complete navigation systems in the literature. These results should encourage new works on computer vision techniques, requirements specification, development, integration, and systematic testing and validation of general navigation systems. In addition to these findings, we also present the complete methodology used for the systematic review, which provides a documentation of the process (allowing quality assessment and repeatability), the criteria for selecting and evaluating the studies, and a framework that can be used for future reviews in this research area.

Autonomous Visual Navigation for Mobile Robots: A Systematic Literature Review

Modern households are becoming more automated thereby delivering convenience and reducing time spent on house chores. While vacuum cleaners have made home cleaning easier, they are largely noisy and bulky for everyday use. It is therefore sine qua non to improve the technology of vacuum cleaning to reduce these deficiencies. Here, we report the development of a compact and efficient vacuum cleaner robot for potential office and home use. The developed robot is disk-shaped, equipped with vacuuming and cleaning technology and controlled by Arduino mega microcontroller. It sucks dirt via a retractable dustbin on top of which a cooling fan is mounted, and two sweepers each driven by a 3 V DC motor. The robot navigates via two motor shield controlled rear wheels and a front caster wheel which also governs its turning. Four ultrasonic sensors, placed at 90° apart, detect obstacles and subsequently help the robot navigate. The robot is powered by 3 batteries (28.8 V DC), rechargeable via an embedded AC-DC adapter. It is 12 cm wide and 9 cm tall making it easy for maneuvering its environment. Because of the light weight battery, cardboard based dustbin and small blower used, its weight is about 1.5 kg. The total current consumed is ∼1102 mA. When fully charged, a 2200 mAh-capacity battery works continuously for two hours and cleans floor efficiently. With this capability, the device will be deployed for office and home use thereby making cleaning a fully autonomous duty.

Development of a vacuum cleaner robot

The autonomous cleaning robot has entered the practical stage, and is getting more and more popular. Currently most researches of the cleaning robot focus on sensor technology, location and environment modeling theory. And these researches have made great progress, which proves the practicability of the cleaning robot further. In this paper, we firstly propose a novel method to mop the floor by using a sponge, and use this method to design a mopping module in the frame work of a multifunction floor cleaning robot. Then the parameters of the module are optimized by analyzing the amount of the pumping out and recycling water. Lastly, a real experiment is carried out to validate the method's effectiveness.

Mopping module design and experiments of a multifunction floor cleaning robot

This paper describes an efficient SLAM system only using RGBD sensors. This system utilizes the Microsoft Kinects to provide visual odometry estimation and 2D range scans. The Kinect looking up toward the ceiling can track the robot's trajectory through visual odometry method, which can provide more accurate motion estimation compared to wheel motion measurement and cannot be disturbed under wheel slippage. This is because the Kinect can provide a color image as well as depth information such that robust 3D feature points matching using invariant 2D feature descriptors such as SURF and FAST is possible. Furthermore, the straight line features on the ceiling can provide additional constraints on the inter-frame motion of the camera and the loop closure leading to a more accurate pose estimate. While the other two contiguous horizontal Kinects can provide wide range scans, which ensure more robust scan matching in the RBPF-SLAM framework. In addition, we develop a novel proposal distribution that relies on visual odometry by replacing the transition motion model to towards a SLAM solution. Subsequently, the accurate grid map is online learnt through the adaptive resample Rao-Blackwellized particle filter. Finally, our experimental results, using three Kinects carried on mobile platform of TurtleBot, clearly show the performance of our method.

An efficient SLAM system only using RGBD sensors

Accurate localization and mapping play a pivotal role in mobile robot navigation. In this paper, we present a novel algorithm for mobile robot SLAM (Simultaneous Localization and Mapping) based on stereo vision. First a novel method is proposed to extract distinctive invariant image features, which is coined PLOT (Polynomial Local Orientation Tensor). The stability of these features to image translation, scaling, rotation and illumination changes makes them suitable landmarks for mobile robot visual SLAM. The visual landmarks relative to the robot can be established by matching the PLOT features. Mobile robot localization is achieved by matching these distinctive landmarks in the current frame to the database map. RANSAC algorithm is improved, coined extended RANSAC, for mobile robot pose estimate due to its efficiency. Meanwhile, the visual landmarks in the database map are updated correspondingly. Experimental results show that the proposed method based on the PLOT features achieves SLAM for mobile robot with higher precision.

Image features-based mobile robot visual SLAM

The invention discloses a gas-adjustable iron core-free linear motor. The motor comprises a base, a line insertion groove, a stator coil and a mover, wherein the line insertion groove is formed on the base; the mover is transversely arranged on the base in a sliding way; a permanent magnet is arranged inside the mover; the mover is formed by splicing a first mover and a second mover positioned on both sides of the stator coil; the first mover and the second mover can move towards or away from each other in a longitudinal direction to adjust the distance between the two movers. The distance between the two movers can be adjusted effectively by moving the two movers, thereby realizing adjustment of the motor gap. When large motor driving force is needed, the two movers are moved towards each other to reduce the gap of the motor, the gap flux density is increased, and strong thrust force is produced by the motor; during high-speed running, the two movers are moved away from each other to increase the gap of the motor, the gap flux density is decreased, the counter electromotive force is reduced, and the resonant counter electromotive force is reduced, so that damages to each element in the motor are reduced, the service life of the motor is prolonged, and the use cost is reduced.

Gas-adjustable iron core-free linear motor

The paper describes a mobile robot application based on monocular vision and laser that recognizes environment objects with capacity of avoiding obstacles in real time. Object recognition algorithm is based on mobile robot vision combining adaptive appearance matching and Kalman filter. The algorithm can adjust color matching threshold adaptively to reduce the influence of brightness variations in the scene. First, it carries out color modeling of environment objects in the YCrCb color space. Then it detects edge features in the image sequence by the Sobel algorithm, and thus to identify the outlines of targets. Finally mobile robot can recognize these objects with high empirical probability under some prior knowledge. Kalman filter is used as our prediction module to search objects in view window instead of the whole image sequence and to reduce calculation time. A virtual sub-targets based algorithm is also presented for real-time obstacles avoidance for mobile robot. Experimental results show that objects recognition algorithm can adapt to brightness variations and is simple, effective, easy to imply and operates with high efficiency. Mobile robot can also avoid obstacles smoothly in real time while navigating in the real scene.

Rui Lin

Papers

Mopping module design and experiments of a multifunction floor cleaning robot

An efficient SLAM system only using RGBD sensors

Image features-based mobile robot visual SLAM

Gas-adjustable iron core-free linear motor

Real-time objects recognition and obstacles avoidance for mobile robot