Hong Bing-rong

Military robots - a glimpse from today and tomorrow

The military forces always tried to use new gadgets and weapons for reducing the risk of their casualties and to defeat their enemies. With the development of sophisticated technology, it mostly relies on the high tech weapons or machinery being used. Robotics is one of the hot fields of modern age in which the nations are concentrating upon for military purposes in the state of war and peace. They have been in use for some time for demining and rescue operations but now they are under research for combat or spy missions. Todays modern military forces are using different kinds of robots for different applications ranging from mine detection, surveillance, logistics and rescue operations. In the future they will be used for reconnaissance and surveillance, logistics and support, communications infrastructure, forward-deployed offensive operations, and as tactical decoys to conceal maneuver by manned assets. In order to make robots for the unpredicted cluttered environment of the battlefield, research on different aspects of robots is under investigation in laboratories to be able to do its job autonomously, as efficiently as a human operated machine can do. Latest techniques are being investigated to have advanced and intelligent robots for different operations. This paper presents different kinds of robotic technologies being used in all the three main forces, Navy, Army and Air. Some of the robots discussed are also being used in the wars of Afghanistan and Iraq, also, the robots that are under investigation in laboratories for future military operations. These robots are under investigation for autonomous and cooperative environment. We focus our attention on the uses of robots in war and peace as well as their impact on society.

Coevolution Based Adaptive Monte Carlo Localization (CEAMCL)

An adaptive Monte Carlo localization algorithm based on coevolution mechanism of ecological species is proposed. Samples are clustered into species, each of which represents a hypothesis of the robots pose. Since the coevolution between the species ensures that the multiple distinct hypotheses can be tracked stably, the problem of premature convergence when using MCL in highly symmetric environments can be solved. And the sample size can be adjusted adaptively over time according to the uncertainty of the robots pose by using the population growth model. In addition, by using the crossover and mutation operators in evolutionary computation, intra-species evolution can drive the samples move towards the regions where the desired posterior density is large. So a small size of samples can represent the desired density well enough to make precise localization. The new algorithm is termed coevolution based adaptive Monte Carlo localization (CEAMCL). Experiments have been carried out to prove the efficiency of the new localization algorithm.

Coevolution Based Adaptive Monte Carlo Localization

Self-localization, a basic problem in mobile robot systems, can be divided into two subproblems: pose tracking and global localization. In pose tracking, the initial robot pose is known, and localization seeks to identify small, incremental errors in a robot’s odometry (Leonard & Durrant-Whyte, 1991). In global localization, however the robot is required to estimate its pose by local and incomplete observed information under the condition of uncertain initial pose. Global localization is a more challenging problem. Only most recently, several approaches based on probabilistic theory are proposed for global localization, including grid-based approaches (Burgard et al., 1996), topological approaches (Kaelbling et al., 1996) (Simmons & Koenig, 1995), Monte Carlo localization (Dellaert et al., 1999) and multi-hypothesis tracking (Jensfelt & Kristensen, 2001) (Roumeliotis & Bekey, 2000). By representing probability densities with sets of samples and using the sequential Monte Carlo importance sampling (Andrieu & Doucet, 2002), Monte Carlo localization (MCL) can represent non-linear and non-Gaussian models well and focus the computational resources on regions with high likelihood. So MCL has attracted wide attention and has been applied in many real robot systems. But traditional MCL has some shortcomings. Since samples are actually drawn from a proposal density, if the observation density moves into one of the tails of the proposal density, most of the samples’ non-normalized importance factors will be small. In this case, a large sample size is needed to represent the true posterior density to ensure stable and precise localization. Another problem is that samples often too quickly converge to a single, high likelihood pose. This might be undesirable in the case of localization in symmetric environments, where multiple distinct hypotheses have to be tracked for extended periods of time. How to get higher localization precision, to improve efficiency and to prevent premature convergence of MCL are the key concerns of the researchers. To make the samples represent the posterior density better, Thrun et al. proposed mixtureMCL (Thrun et al., 2001), but it needs much additional computation in the sampling process. To improve the efficiency of MCL, methods adjusting sample size adaptively over time are proposed (Fox, 2003) (Koller & Fratkina, 1998), but they increase the probability of premature convergence. Although clustered particle filters are applied to solve premature convergence (Milstein et al., 2002), the method loses the advantage of focusing the computational resources on regions with high likelihood because it maintains the same sample size for all clusters. In this paper, a new version of MCL is proposed to overcome those limitations. Samples are clustered into groups which are also called species. A coevolutionary model derived from competition of ecological species is introduced to

Novel Method for Monocular Vision Based Mobile Robot Localization

A robust environment map with 3D spatial natural landmarks that facilitates monocular vision based mobile robot for global localization is built. The highly distinctive multi-dimensional vector descriptors associated with the features extracted through scale invariant feature transform (SIFT) can be robustly matched despite changes in illumination, scale and viewpoint. The landmarks are 3D restructured with the matching image feature pairs obtained through the KD-tree based nearest search approach. Novel RANSAC approach based on generic optimization for global localization is presented. Experiments on the robot Pioneer3 with monocular vision in our real indoor environment show that our method is of high precision

Novel Mobile Robot Simultaneous Loclization and Mapping Using Rao-Blackwellised Particle Filter

This paper presents the novel method of mobile robot simultaneous localization and mapping (SLAM), which is implemented by using the Rao-Blackwellised particle filter (RBPF) for monocular vision-based autonomous robot in unknown indoor environment. The particle filter is combined with unscented Kalman filter (UKF) to extending the path posterior by sampling new poses that integrate the current observation. The landmark position estimation and update is implemented through the unscented transform (UT). Furthermore, the number of resampling steps is determined adaptively, which seriously reduces the particle depletion problem. Monocular CCD camera mounted on the robot tracks the 3D natural point landmarks, which are structured with matching image feature pairs extracted through Scale Invariant Feature Transform (SIFT). The matching for multi-dimension SIFT features which are highly distinctive due to a special descriptor is implemented with a KD-Tree in the time cost of O(log2N). Experiments on the robot Pioneer3 in our real indoor environment show that our method is of high precision and stability.

An object-oriented data framework for virtual environments with hierarchical modeling

Virtual reality technology, which is cyberspace composed of multimedia, is a field of comprehensive technology. It is of three basic feathers, namely, interaction, immersion and imagination so that we have to cope with the need for extremely large data sets, massive amounts of computation, and high-throughput networking. This paper presents an approach for object-oriented data modeling framework of complicated virtual environments. The paper discusses the hierarchical decomposition of objects in virtual environments and reuse of these object data libraries to constitute model of virtual environments. This modeling approach used in the paper makes sure that modeling data can be inherited, modularized, maintained easily so as to control redundant data and reduce the software development time, at the same time, realizes dynamic behaviors of objects to meet the needs of some changes of virtual environments.

Cooperative Exploration by Multi-robots without Global Localization

Efficient exploration of unknown environments is a fundamental problem in mobile robotics. We propose a novel topological map whose nodes are represented with the range finders free beams together with the visual scale-invariant features. The topological map enables teams of robots to efficiently explore environments from different, unknown locations without knowing their initial poses, relative poses and global poses in a certain world reference frame. The experiments of map merging and coordinated exploration demonstrate the proposed map is not only easy for merging, but also convenient for robust and efficient explorations in unknown environments.

Autonomous navigation based on the velocity space method in dynamic environments

We present a new local obstacle avoidance approach for mobile robots in partially known environments on the basis of the curvature-velocity method (CVM), the lane-curvature method (LCM) and the beam-curvature method (BCM). Not only does this method inherit the advantages from both BCM and LCM, but also it combines the prediction model of collision with BCM perfectly so that the so-called prediction based BCM (PBCM) comes into being and can be used to avoid moving obstacles in dynamic environments.We present a new local obstacle avoidance approach for mobile robots in partially known environments on the basis of the curvature-velocity method (CVM), the lane-curvature method (LCM) and the beam-curvature method (BCM). Not only does this method inherit the advantages from both BCM and LCM, but also it combines the prediction model of collision with BCM perfectly so that the so-called prediction based BCM (PBCM) comes into being and can be used to avoid moving obstacles in dynamic environments.

Dynamic growth of robot formation using only local sensing and minimal communication

This paper presents a behavior based, decentralized approach for robot formations. The formation grows from single robot to a maximum possible number of robots while in motion. The robots that are in the formation always try to keep a regular polygon and hence made a virtual circle in the end. This global behavior of forming dynamic formation is achieved using each robots local sensing and interaction. The robots are using sensors like lasers, sonar and vision for sensing distance and recognizing objects. The main objective of any robot in the group is to keep its neighbor in view by panning the camera at an angle required for making a regular polygon. The formation could be expanded with the addition of a new member while in motion and then each member re-calculates its position based on the number of robots, and the ultimate shape. We tested our algorithm on simulation and discussed the issues related to the hardware solution.

A multi-agent coordination communication paradigm in adversarial periodic team synchronization environment

A communication paradigm is proposed for multi-agent coordination in dynamic, real time and adversarial PTS environment. This paper analyses the issues agent must solve for the purpose of better coordination and presents the design of paradigm. Finally, the application of the paradigm in RoboCup and MiroSot Simulated Soccer Game and the experiments demonstrate that our communication paradigm improved coordination in robots and increased the probability of winning game.