An Intelligent Path Planning Approach for Humanoid Robots Using Adaptive Particle Swarm Optimization

The current investigation is focused on the development of a novel navigational controller for the optimized path planning and navigation of humanoid robots. The proposed navigational controller works on the principle of adaptive particle swarm optimization. To improve the working pattern of a simple particle swarm optimization controller, some modifications are done to the controlling parameters of the algorithm. The input parameters to the controller are the sensory information in forms of obstacle distances, and the output from the controller is the required turning angle to safely reach the target position by avoiding the obstacles present in the path. By applying the logic of the adaptive particle swarm optimization, humanoid robots are tested in simulation environments. To validate the results, an experimental platform is also developed under laboratory conditions, and a comparison has been performed between the simulation and experimental results. To test the proposed controller in both static and dynamic environments, it is implemented in the navigation of single as well as multiple humanoid robots. Finally, to ensure the efficacy of the proposed controller, it is compared with some of the existing techniques available for navigational purpose.

Cerebellum-inspired neural network solution of the inverse kinematics problem

The demand today for more complex robots that have manipulators with higher degrees of freedom is increasing because of technological advances. Obtaining the precise movement for a desired trajectory or a sequence of arm and positions requires the computation of the inverse kinematic (IK) function, which is a major problem in robotics. The solution of the IK problem leads robots to the precise position and orientation of their end-effector. We developed a bioinspired solution comparable with the cerebellar anatomy and function to solve the said problem. The proposed model is stable under all conditions merely by parameter determination, in contrast to recursive model-based solutions, which remain stable only under certain conditions. We modified the proposed model for the simple two-segmented arm to prove the feasibility of the model under a basic condition. A fuzzy neural network through its learning method was used to compute the parameters of the system. Simulation results show the practical feasibility and efficiency of the proposed model in robotics. The main advantage of the proposed model is its generalizability and potential use in any robot.

Model-Based Footstep Planning Method for Biped Walking on 3D Field

<div class=""abs_img""> <img src=""[disp_template_path]/JRM/abst-image/00270002/05.jpg"" width=""300"" /> Footstep planning on the 3D field</div> This paper proposes a model-based 3D footstep planning method. A discrete-time kinematic model, in which vertical motions are independent of horizontal motions, describes the biped walking of the humanoid robot. The 3D field environment is represented by geographical features divided into the meshes, determined from measurements obtained by a sensor, where the inclinations in each mesh are assumed. The optimal plan is obtained by solving a constrained optimization problem based on the foot placements of the model. A goal-tracking evaluation of the problem on horizontal foot placements is carried out to reach the goal, while vertical motions are adopted to meet constraints consisting of the foot workspace and contact with the 3D field surface. A quadratic programming method is implemented to solve the problem based on the humanoid robot NAO in real time. </span>

Analyzing locomotion synthesis with feature-based motion graphs

We propose feature-based motion graphs for realistic locomotion synthesis among obstacles. Among several advantages, feature-based motion graphs achieve improved results in search queries, eliminate the need of postprocessing for foot skating removal, and reduce the computational requirements in comparison to traditional motion graphs. Our contributions are threefold. First, we show that choosing transitions based on relevant features significantly reduces graph construction time and leads to improved search performances. Second, we employ a fast channel search method that confines the motion graph search to a free channel with guaranteed clearance among obstacles, achieving faster and improved results that avoid expensive collision checking. Lastly, we present a motion deformation model based on Inverse Kinematics applied over the transitions of a solution branch. Each transition is assigned a continuous deformation range that does not exceed the original transition cost threshold specified by the user for the graph construction. The obtained deformation improves the reachability of the feature-based motion graph and in turn also reduces the time spent during search. The results obtained by the proposed methods are evaluated and quantified, and they demonstrate significant improvements in comparison to traditional motion graph techniques.

Capuchin: A Free-Climbing Robot

This paper describes an integrated quasi-autonomous four-limbed robot, named Capuchin, which is equipped with appropriate sensing, planning and control capabilities to “free-climb” vertical terrain. Unlike aid climbing that takes advantage of special tools and/or engineered terrain features, free climbing only relies on friction at the contacts between the climber and the rigid terrain. While moving, Capuchin adjusts its body posture (hence, the position of its centre of mass) and exerts appropriate forces at the contacts in order to remain in equilibrium. Vision is used to achieve precise contacts and force sensing to control contact forces. The robot's planner is based on a pre-existing two-stage “stance-before-motion” approach. Its controller applies a novel “lazy” force control strategy that performs force adjustments only when these are needed. Experiments demonstrate that Capuchin can reliably climb vertical terrain with irregular features.

Reverse control for humanoid robot task recognition

Efficient methods to perform motion recognition have been developed using statistical tools. Those methods rely on primitive learning in a suitable space, for example, the latent space of the joint angle and/or adequate task spaces. Learned primitives are often sequential: A motion is segmented according to the time axis. When working with a humanoid robot, a motion can be decomposed into parallel subtasks. For example, in a waiter scenario, the robot has to keep some plates horizontal with one of its arms while placing a plate on the table with its free hand. Recognition can thus not be limited to one task per consecutive segment of time. The method presented in this paper takes advantage of the knowledge of what tasks the robot is able to do and how the motion is generated from this set of known controllers, to perform a reverse engineering of an observed motion. This analysis is intended to recognize parallel tasks that have been used to generate a motion. The method relies on the task-function formalism and the projection operation into the null space of a task to decouple the controllers. The approach is successfully applied on a real robot to disambiguate motion in different scenarios where two motions look similar but have different purposes.