ONLINE DYNAMICALLY BALANCED ASCENDING AND DESCENDING GAIT GENERATIONS OF A BIPED ROBOT USING SOFT COMPUTING

2007 ◽  
Vol 04 (04) ◽  
pp. 777-814 ◽  
Author(s):  
PANDU RANGA VUNDAVILLI ◽  
SAMBIT KUMAR SAHU ◽  
DILIP KUMAR PRATIHAR
Keyword(s):  
Soft Computing ◽  
Large Scale ◽  
Fuzzy Logic Controller ◽  
Dynamic Balance ◽  
Biped Robot ◽  
Legged Robot ◽  
Gait Generation ◽  
Natural Choice ◽  
Rule Bases ◽  
Generation Problem

In the present paper, two algorithms based on soft computing have been developed for dynamically balanced gait generations of a biped robot ascending and descending a staircase. The utility of the soft computing tools is best justified, when the data available for the problem to be solved are imprecise in nature, difficult to model and exhibit large-scale solution spaces. The problem of online gait generation of a biped robot exhibits such a complex phenomenon, and ultimately soft computing has become a natural choice for solving it. The gait generation problems of a biped robot have been solved using two different approaches, namely genetic-neural (GA-NN) and genetic-fuzzy (GA-FLC) systems. In GA-NN, the gait generation problem of a two-legged robot has been modeled using two modules of Neural Network (NN), whose weights are optimized offline using a Genetic Algorithm (GA), whereas in GA-FLC, the above problem is modeled utilizing two modules of Fuzzy Logic Controller (FLC) and their rule bases are optimized offline using a GA. Once optimized, the GA-NN and GA-FLC systems will be able to generate dynamically balanced gaits of the biped robot online. The performances of the two approaches are compared with respect to the Dynamic Balance Margin (DBM).

Near-Optimal Trajectory Generation of a Two-Legged Robot with Soft Sole on Staircase using PSO and ABC

2015 ◽  
Vol 3 (2) ◽  
pp. 1-19
Author(s):  
Naga Sudha Rani B ◽  
Vundavilli Pandu Ranga
Keyword(s):  
Dynamic Balance ◽  
Reaction Force ◽  
Biped Robot ◽  
Legged Robot ◽  
Walking Machine ◽  
Bee Colony ◽  
Zero Moment ◽  
Lumped Masses ◽  
Least Energy ◽  
Generation Problem

During biped locomotion the foot ground interaction plays an important role, as it takes the reaction force acting on the foot and allows stable walking of the biped robot. Generally, the foot is considered to be hard to solve the gait generation problem and dynamic balance aspects of the two-legged robot. However, a layer of rubber is placed on the sole of the robot to act as a shock absorber for all practical purposes. It is important to note that the soft sole gets deformed during walking of the robot and allows the limbs of the robot to bend that influences the dynamic balance of the walking machine. The aim of this study is to use two different non-traditional optimization algorithms, such as particle swarm optimization (PSO) and artificial bee colony (ABC) algorithms to obtain the optimal hip trajectory, damping coefficient and position of the lumped masses for a 7-DOF biped robot ascending the staircase. The dynamic balance of the gaits generated with soft sole is verified using the concept of zero moment point (ZMP). Further, the energy consumed in ascending the staircase with and without soft sole has been computed. The results of this study proved that, least energy is consumed with soft sole having correction for the deformation.

Generating real-time trajectories for a planar biped robot crossing a wide ditch with landing uncertainties

Robotica ◽  
2018 ◽  
Vol 37 (1) ◽  
pp. 109-140 ◽  
Author(s):  
V. Janardhan ◽  
R. Prasanth Kumar
Keyword(s):  
Real Time ◽  
Degrees Of Freedom ◽  
Dynamic Balance ◽  
Surface Friction ◽  
Biped Robot ◽  
Net Energy ◽  
Leg Length ◽  
Uncertain Environments ◽  
Novel Concept ◽  
Time Planning

SUMMARYDitch crossing is one of the essential capabilities required for a biped robot in disaster management and search and rescue operations. Present work focuses on crossing a wide ditch with landing uncertainties by an under-actuated planar biped robot with five degrees of freedom. We consider a ditch as wide for a robot when the ankle to ankle stretch required to cross it is at least equal to the leg length of the robot. Since locomotion in uncertain environments requires real-time planning, in this paper, we present a new approach for generating real-time joint trajectories using control constraints not explicitly dependent on time, considering impact, dynamic balance, and friction. As part of the approach, we introduce a novel concept called the point of feasibility for bringing the biped robot to complete rest at the end of ditch crossing. We present a study on the influence of initial posture on landing impact and net energy consumption. Through simulations, we found the best initial postures to efficiently cross a wide ditch of width 1.05 m, with less impact and without singularities. Finally, we demonstrate the advantage of the proposed approach to cross a wide ditch when the surface friction is not same on both sides of the ditch.

Control of a legged robot

2015 ◽  
Vol 24 (1-2) ◽  
pp. 53-57
Author(s):  
Maxime Sadre
Keyword(s):  
Reference Model ◽  
Stabilization Energy ◽  
Main Task ◽  
Legged Robot ◽  
Energy Shaping ◽  
Gait Generation ◽  
System A ◽  
Nonlinear Energy

AbstractThis paper deals with the control of hopping and running systems that interact intermittently with the environment. The control, based on a nonlinear energy reference model, has the main task of conferring to the system, a periodic stable behavior. This approach may be used for gait generation, nominal stance stabilization, energy shaping, and optimization.

Measuring Human Intelligence by Applying Soft Computing Techniques

2013 ◽  
pp. 130-155
Author(s):  
Kunjal Mankad ◽  
Priti Srinivas Sajja
Keyword(s):  
Soft Computing ◽  
Fitness Function ◽  
Fuzzy Rule ◽  
Managerial Skills ◽  
Intelligent Decision Support System ◽  
Intelligent Decision ◽  
Soft Computing Techniques ◽  
Rule Bases ◽  
Encoding Strategy ◽  
Intelligent Decision Support

The chapter focuses on Genetic-Fuzzy Rule Based Systems of soft computing in order to deal with uncertainty and imprecision with evolving nature for different domains. It has been observed that major professional domains such as education and technology, human resources, psychology, etc, still lack intelligent decision support system with self evolving nature. The chapter proposes a novel framework implementing Theory of Multiple Intelligence of education to identify students’ technical and managerial skills. Detail methodology of proposed system architecture which includes the design of rule bases for technical and managerial skills, encoding strategy, fitness function, cross-over and mutation operations for evolving populations is presented in this chapter. The outcome and the supporting experimental results are also presented to justify the significance of the proposed framework. It concludes by discussing advantages and future scope in different domains.

Sign in / Sign up

Export Citation Format

Share Document