Search results

It has been an ultimate long‐term dream in robotics and AI fields to build robotic systems with life‐like appearance, behaviours and intelligence, reflected by many science fiction books and films. This is also an extremely challenging task. This paper introduces our current research efforts to build a multi‐agent system for cooperation and learning of multiple life‐like robots in the RoboCup domain. A behaviour‐based hierarchy is proposed for the Essex Rovers robot football team to achieve intelligent actions in real time, which includes both a neural network‐based color detection algorithm and a fuzzy logic controller. Preliminary results based on legged locomotion experiments of Sony walking robots are presented.

Autonomous mobile robots (AMRs) play a crucial role in industrial and service fields. The paper aims to build a LiDAR-based simultaneous localization and mapping (SLAM) system used by AMRs to overcome challenges in dynamic and changing environments.

This research introduces SLAM-RAMU, a lifelong SLAM system that addresses these challenges by providing precise and consistent relocalization and autonomous map updating (RAMU). During the mapping process, local odometry is obtained using iterative error state Kalman filtering, while back-end loop detection and global pose graph optimization are used for accurate trajectory correction. In addition, a fast point cloud segmentation module is incorporated to robustly distinguish between floor, walls and roof in the environment. The segmented point clouds are then used to generate a 2.5D grid map, with particular emphasis on floor detection to filter the prior map and eliminate dynamic artifacts. In the positioning process, an initial pose alignment method is designed, which combines 2D branch-and-bound search with 3D iterative closest point registration. This method ensures high accuracy even in scenes with similar characteristics. Subsequently, scan-to-map registration is performed using the segmented point cloud on the prior map. The system also includes a map updating module that takes into account historical point cloud segmentation results. It selectively incorporates or excludes new point cloud data to ensure consistent reflection of the real environment in the map.

The performance of the SLAM-RAMU system was evaluated in real-world environments and compared against state-of-the-art (SOTA) methods. The results demonstrate that SLAM-RAMU achieves higher mapping quality and relocalization accuracy and exhibits robustness against dynamic obstacles and environmental changes.

Compared to other SOTA methods in simulation and real environments, SLAM-RAMU showed higher mapping quality, faster initial aligning speed and higher repeated localization accuracy.

Landmark‐based navigation of autonomous mobile robots or vehicles has been widely adopted in industry. Such a navigation strategy relies on identification and subsequent recognition of distinctive environment features or objects that are either known a priori or extracted dynamically. This process has inherent difficulties in practice due to sensor noise and environment uncertainty. This paper is to propose a navigation algorithm that simultaneously locates the robots and updates landmarks in a manufacturing environment. A key issue being addressed is how to improve the localization accuracy for mobile robots in a continuous operation, in which the Kalman filter algorithm is adopted to integrate odometry data with scanner data to achieve the required robustness and accuracy. The Kohonen neural networks have been used to recognize landmarks using scanner data in order to initialize and recalibrate the robot position by means of triangulation when necessary.

Today’s Internet technology provides a convenient way for us to develop an integrated network environment for the diversified applications of different robotic systems. To be successful in real‐world applications, Internet‐based robots require a high degree of autonomy and local intelligence to deal with the restricted bandwidth and arbitrary transmission delay of the Internet. This paper describes the first step toward building such an Internet‐based robotic system for teleoperation in the University of Essex. The system has a standard network protocol and an interactive human‐machine interface. Using a Web browser, a remote operator can control the mobile robot to navigate in our laboratory with visual feedback and a simulated environment map via the Internet. The employment of an intuitive user interface enables Internet users to control the mobile robot and implement useful tasks remotely. Although at its first stage, the developed system has the potential to be extended to many real‐world applications such as tele‐manufacturing, tele‐training and tele‐service.

This paper presents an evolutionary algorithm (EA) for Sony legged robots to learn good walking behaviours with little or no interaction with the designers. Once the learning method is put into place, the module can learn through its interaction with the real world.

An EA for developing locomotion gaits of quadruped walking robots is presented in this paper. It is based on a hybrid approach that changes the probability of genetic operators in respect to the performance of the operator's offspring.

The mutating and combination behaviours of the genetic algorithms allow the process to develop a useful behaviour over time. The resulting gait from this training proved to be a better solution than the non‐interference training for movements over all types of surfaces, pointing to a local optima being discovered in the non‐environmental interference situation.

The behaviour of these algorithms is stochastic so that they may potentially present different solutions in different runs of the same algorithm. The mechanism described here has several features that should be noted. It allows rapid parameterisation of operator probabilities across the range of potential genetic algorithms and operator set. It is tailored to a steady state reproduction scheme. It would not be literally applicable to problems with noisy evaluation functions.

Provides novel application of genetic algorithms to a potentially practical application area.

This paper presents a novel hands‐free control system for intelligent wheelchairs (IWs) based on visual recognition of head gestures.

A robust head gesture‐based interface (HGI), is designed for head gesture recognition of the RoboChair user. The recognised gestures are used to generate motion control commands to the low‐level DSP motion controller so that it can control the motion of the RoboChair according to the user's intention. Adaboost face detection algorithm and Camshift object tracking algorithm are combined in our system to achieve accurate face detection, tracking and gesture recognition in real time. It is intended to be used as a human‐friendly interface for elderly and disabled people to operate our intelligent wheelchair using their head gestures rather than their hands.

This is an extremely useful system for the users who have restricted limb movements caused by some diseases such as Parkinson's disease and quadriplegics.

In this paper, a novel integrated approach to real‐time face detection, tracking and gesture recognition is proposed, namely HGI.

It is an useful human‐robot interface for IWs.

This paper seeks to present an inertial motion tracking system for monitoring movements of human upper limbs in order to support a home‐based rehabilitation scheme in which the recovery of stroke patients' motor function through repetitive exercises needs to be continuously monitored and appropriately evaluated.

Two inertial sensors are placed on the upper and lower arms in order to obtain acceleration and turning rates. Then the position of the upper limbs can be deduced by using the kinematical model of the upper limbs that was designed in the previous paper. The tracking system starts from inertial data acquisition and pre‐filtering, followed by a number of processes such as transformation of coordinate systems of sensor data, and kinematical modelling and optimization of position estimation.

The motion detector using the proposed kinematic model only has drifts in the measurements. Fusion of acceleration and orientation data can effectively solve the drift problem without the involvement of a Kalman filter.

The image rendering is not undertaken when the data sampling is performed. This non‐synchronization is applied in order to avoid the breaks in the continuous sampling.

This new motion detector can work in different environments without significant drifts. Also, this system only deploys two inertial sensors but is able to estimate the position of the wrist, elbow and shoulder joints.

Robots operating in the real world should be able to make decisions and plan ahead their actions. We argue that learning using generalized representations of the robot's experience can assist such a ability.

We present results from our research on methods for enabling mobile robots to plan their actions using generalized representations of their experience. Such generalized representations are acquired through a learning phase during which the robot explores its environment and builds subsymbolic (connectionist) representations of the result that its actions have to its sensory perception. Then these representations are employed by the robot for autonomously determining task‐achieving sequences of actions (plans),for attaining assigned tasks.

Such subsymbolic mechanisms can employ generalization techniques in order to pursue plans through unexplored regions of the robot's environment.

Subsymbolic motion planning can autonomously determine task‐achieving sequences of actions in real environments, without using presupplied symbolic knowledge, but instead generating novel plans using previously acquired subsymbolic representations.

The main purpose of this paper is to investigate two key elements of localization and mapping of Autonomous Underwater Vehicle (AUV), i.e. to overview various sensors and algorithms used for underwater localization and mapping, and to make suggestions for future research.

The authors first review various sensors and algorithms used for AUVs in the terms of basic working principle, characters, their advantages and disadvantages. The statistical analysis is carried out by studying 35 AUV platforms according to the application circumstances of sensors and algorithms.

As real‐world applications have different requirements and specifications, it is necessary to select the most appropriate one by balancing various factors such as accuracy, cost, size, etc. Although highly accurate localization and mapping in an underwater environment is very difficult, more and more accurate and robust navigation solutions will be achieved with the development of both sensors and algorithms.

This paper provides an overview of the state of art underwater localisation and mapping algorithms and systems. No experiments are conducted for verification.

The paper will give readers a clear guideline to find suitable underwater localisation and mapping algorithms and systems for their practical applications in hand.

There is a wide range of audiences who will benefit from reading this comprehensive survey of autonomous localisation and mapping of UAVs.

The paper will provide useful information and suggestions to research students, engineers and scientists who work in the field of autonomous underwater vehicles.