The aim of this work has been the implementation and testing in real conditions of a new algorithm based on the cell-mapping techniques and reinforcement learning methods to obtain the optimal motion planning of a vehicle considering kinematics, dynamics and obstacle constraints. The algorithm is an extension of the control adjoining cell mapping technique for learning the dynamics of the vehicle instead of using its analytical state equations. It uses a transformation of cell-to-cell mapping in order to reduce the time spent during the learning stage. Real experimental results are reported to show the satisfactory performance of the algorithm.

In this paper, a planar 3-DOF XYγ parallel micromanipulator with monolithic structure is presented. The micromanipulator is driven by three piezoelectric (PZT) actuators. To achieve highly accurate control, a new approach investigating the relationship among input-force, payload, stiffness, and displacement (IPSD model) of the XYγ micromanipulator is proposed in analytical style, and the analytical expression of the relationship between driving voltages of PZT actuators and outputs of end-effector is deduced based on the IPSD model. Finally, in order to verify the IPSD model, the simulations by finite element method and experiment are performed. The micromanipulator can be used to do microtasks that need the manipulator perform only planar motion, such as microoperation and microassembly, and the proposed IPSD model is useful for both digital control and design of the XYγ micromanipulator.

The recent developments in applications that have been designed to increase road safety require reliable and trustworthy sensors. Keeping this in mind, the most up-to-date research in the field of automotive technologies has shown that LIDARs are a very reliable sensor family. In this paper, a new approach to road obstacle classification is proposed and tested. Two different LIDAR sensors are compared by focusing on their main characteristics with respect to road applications. The viability of these sensors in real applications has been tested, where the results of this analysis are presented.

Spherical robot is a special kind of nonholonomic system that cannot be converted to chained form, which means most of the well-known control methodologies are not suitable for this system. For the trajectory tracking of BHQ-1, a spherical robot designed by our lab, a two-state trajectory tracking controller is proposed in this paper. First, the kinematic model of the robot is built using screw theory and exponential method and the controllability is proved based on the differential geometric control theory. Then to solve the two-state trajectory tracking problem of BHQ-1, a shunting model of neurodynamics and Lyapunov's direct method are combined to design a two-state trajectory tracking controller, of which the Lyapunov stability is validated. Finally, typical simulation examples, such as tracking linear, circular, and sinusoidal trajectories, are introduced to verify the effectiveness of the proposed controller. In this paper the proposed method can also be applied to the control of other spherical robots.

This paper addresses the map merging problem, which is the most important issue in multi-robot simultaneous localization and mapping (SLAM) using the Rao–Blackwellized particle filter (RBPF-SLAM) with unknown initial poses. The map merging is performed using the map transformation matrix and the pair of map merging bases (MMBs) of the robots. However, it is difficult to find appropriate MMBs because each robot pose is estimated under multi-hypothesis in the RBPF-SLAM. In this paper, probabilistic map merging (PMM) using the Gaussian process is proposed to solve the problem. The performance of PMM was verified by reducing errors in the merged map with computer simulations and real experiments.

In this paper, a family of discriminant functions is defined for searching isotropic configurations in robot manipulators. A subfamily of the functions extensively exploits properties of symmetric polynomials derived from a manipulability matrix. The complexity analysis of computing the discriminant functions is provided. Possible applications of the functions are mentioned and illustrated.

In order to achieve the autonomy of mobile robots, effective localization is a necessary prerequisite. In this paper, we propose an improved Monte Carlo localization algorithm using self-adaptive samples (abbreviated as SAMCL). By employing a pre-caching technique to reduce the online computational burden, SAMCL is more efficient than the regular MCL. Further, we define the concept of similar energy region (SER), which is a set of poses (grid cells) having similar energy with the robot in the robot space. By distributing global samples in SER instead of distributing randomly in the map, SAMCL obtains a better performance in localization. Position tracking, global localization and the kidnapped robot problem are the three sub-problems of the localization problem. Most localization approaches focus on solving one of these sub-problems. However, SAMCL solves all the three sub-problems together, thanks to self-adaptive samples that can automatically separate themselves into a global sample set and a local sample set according to needs. The validity and the efficiency of the SAMCL algorithm are demonstrated by both simulations and experiments carried out with different intentions. Extensive experimental results and comparisons are also given in this paper.

Vision sensors are increasingly being used in the implementation of Simultaneous Localization and Mapping (SLAM). Even though the mathematical framework of SLAM is well understood, considerable issues remain to be resolved when a particular sensing modality is considered. For instance, the observation model of a small baseline stereo camera is known to be highly nonlinear. As a consequence, state estimations obtained from standard recursive estimators, such as the Extended Kalman Filter, tend to be inconsistent. Further, vision-based approaches are plagued with high feature densities, and the consequent requisite of maintaining large feature databases for loop closure and data association. This paper proposes a two-tier solution for resolving these issues, inspired by the mechanics of human navigation. The proposed two-tier solution addresses the consistency issue by formulating the SLAM problem as a nonlinear batch optimization and presents a novel method for feature management through a two-tier map representation. Simulations and experiments are carried out in an office-like environment to validate the performance of the algorithm.

This paper presents a model of a three-joint (four links) carangiform fish robot. The smooth gait or smooth motion of a fish robot is optimized by using a combination of the Genetic Algorithm (GA) and the Hill Climbing Algorithm (HCA) with respect to its dynamic system. Genetic algorithm is used to create an initial set of optimal parameters for the two input torque functions of the system. This set is then optimized by using HCA to ensure that the final set of optimal parameters is a “near” global optimization result. Finally, the simulation results are presented in order to demonstrate that the proposed method is effective.

In this paper, we present the design, static analysis, simulation, and implementation of a novel design for a naturally stable climbing robot that has been inspired from human pole/tree climbers. The other benefits of this robot, besides being naturally stable, are its simple design, ease of control, light weight, simple mechanism, and fast climbing speed. The robot consists of three wheels, two free and one active wheel, which enable the robot to climb or descend poles. The free wheels are almost frictionless, while the active wheel has enough friction to be able to apply force on the pole for stable climbing or descending. The wheels are designed in V-shape such that the robot can compensate for misplacements eliminating possible detachment from poles. Although the robot can operate with a single free wheel, however, an extra free wheel is added to increase the stability and safety of the robot. In this paper, the static analysis of the robot is presented and the robot is simulated. Furthermore, the robot is actually implemented and successfully tested in two sizes, a small size and a big/full size. The full-scale prototype has been equipped with washing and inspection tools and tested washing actual street lights. The results show the unique characteristics of this robot that make it more stable if more weight is carried.

This paper proposes a feasible variation of approximate grid-based path-planning methods, which have been replaced with probabilistic methods nowadays, due mainly to their impracticality in high-dimensional spaces. Our aim is to demonstrate that, with an incremental exploration of the CSpace by means of Interpolated walk primitives and ANY-Time algorithms, we can generate – online – high-quality solutions that can be compared with probabilistic methods and can even improve some aspects, such as the completeness. Computational time, path smoothness, path clearance, and path distance are the qualifiers used to evaluate the path planner. These quality factors are critical in robotics. In fact, in both mobile and industrial robots, the computational time is a primary requirement to work online, the clearance gives security to the movements of the robot, and the smoothness can prolong the life of the mechanical components. Our method has been compared to probabilistic path planners, with the feasibility and benefits of our algorithm being proved in terms of the quality factors aforementioned.

In this paper, the definition of generalized symmetric Gough–Stewart parallel manipulators is presented. The concept of dynamic isotropy is proposed and the singular values of the bandwidth matrix are introduced to evaluate dynamic isotropy and solved analytically. Considering the payload's mass-geometry characteristics, the formulations for completely dynamic isotropy are derived in close form. It is proven that a generalized symmetric Gough–Stewart parallel manipulator is easer to achieve dynamic isotropy and applicable in engineering applications. An optimization procedure based on particle swarm optimization is proposed to obtain better dexterity and large singularity-free workspace, which guarantees the optimal solution and gives mechanically feasible realization.

We have proposed a new repetition framework for vision-based behavior imitation by a sequence of multiple humanoid robots, introducing an on-line method for delimiting a time-varying context. This novel approach investigates the ability of a robot “student” to observe and imitate a behavior from a “teacher” robot; the student later changes roles to become the “teacher” for a naïve robot. For the many robots that already use video acquisition systems for their real-world tasks, this method eliminates the need for additional communication capabilities and complicated interfaces. This can reduce human intervention requirements and thus enhance the robots' practical usefulness outside the laboratory. Articulated motions are modeled in a three-layer method and registered as learned behaviors using color-based landmarks. Behaviors were identified on-line after each iteration by inducing a decision tree from the visually acquired data. Error accumulated over time, creating a context drift for behavior identification. In addition, identification and transmission of behaviors can occur between robots with differing, dynamically changing configurations. ITI, an on-line decision tree inducer in the C4.5 family, performed well for data that were similar in time and configuration to the training data but the greedily chosen attributes were not optimized for resistance to accumulating error or configuration changes. Our novel algorithm, OLDEX identified context changes on-line, as well as the amount of drift that could be tolerated before compensation was required. OLDEX can thus identify time and configuration contexts for the behavior data. This improved on previous methods, which either separated contexts off-line, or could not separate the slowly time-varying context into distinct regions at all. The results demonstrated the feasibility, usefulness, and potential of our unique idea for behavioral repetition and a propagating learning scheme.