Center for and Robotics

Bangalore, India

Center for and Robotics

Bangalore, India
SEARCH FILTERS
Time filter
Source Type

Savitha D.K.,Center for and Robotics | Rakshit S.,Center for and Robotics
International Conference on "Emerging Trends in Robotics and Communication Technologies", INTERACT-2010 | Year: 2010

For any autonomous system it is very important to acquire the knowledge of the surrounding environment. Images and videos acquired by the vision based sensors can provide meaningful information about the environment, which can be very useful for the navigation of autonomous system like mobile robots. To extract road information from image frames for navigation purpose they have to be classified. Classification is the process of assigning label to the image pixels. Gaussian Mixture Model (GMM) is a model based segmentation method to group image pixels, where the parameters of the model are learned by Expectation Maximization (EM) algorithm. This paper we introduce a top-down supervised learning to assign logical labels to multiple modes created by GMM. This paper also explains the rejection criteria implemented in GMM based classification, which ensures that only pixels with strong road signature are assigned to road class. Contiguity is also applied to get robust classification output. These enable meaningful classification of images of same or similar scenes. © 2010 IEEE.


Menon M.S.,Indian Institute of Science | Ravi V.C.,Center for and Robotics | Ghosal A.,Indian Institute of Science
Journal of Mechanisms and Robotics | Year: 2017

Hyper-redundant snakelike serial robots are of great interest due to their application in search and rescue during disaster relief in highly cluttered environments and recently in the field of medical robotics. A key feature of these robots is the presence of a large number of redundant actuated joints and the associated well-known challenge of motion planning. This problem is even more acute in the presence of obstacles. Obstacle avoidance for point bodies, nonredundant serial robots with a few links and joints, and wheeled mobile robots has been extensively studied, and several mature implementations are available. However, obstacle avoidance for hyper-redundant snakelike robots and other extended articulated bodies is less studied and is still evolving. This paper presents a novel optimization algorithm, derived using calculus of variation, for the motion planning of a hyper-redundant robot where the motion of one end (head) is an arbitrary desired path. The algorithm computes the motion of all the joints in the hyper-redundant robot in a way such that all its links avoid all obstacles present in the environment. The algorithm is purely geometric in nature, and it is shown that the motion in free space and in the vicinity of obstacles appears to be more natural. The paper presents the general theoretical development and numerical simulations results. It also presents validating results from experiments with a 12-degree-of-freedom (DOF) planar hyper-redundant robot moving in a known obstacle field. © 2017 by ASME.


Panigrahi N.,Center for and Robotics
Journal of the Indian Society of Remote Sensing | Year: 2015

Different classification techniques are being designed and under usage for classification of hyper spectral images. The usage of these classifiers differ for different type of hyper spectral data and application domain. The performance of these classifiers are influenced by feature preprocessing stage. In this research work we have investigated the impact of feature preprocessing using Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) on classification stage. The experiment is carried out using three sets of hyperspectral data. Classifications were carried out using three different classification techniques namely Maximum Likelihood Estimation (MLE), Constraint Energy Minimization (CEM) and Spectral Angle Mapper (SAM) on the preprocessed hyperspectral data. It is observed that the impact of PCA and LDA on the classification techniques are in two aspects (a) The preprocessing techniques facilitates to achieve high classification accuracy even with less number of training features and (b) Preprocessing expedites the classification process for large data sets. Also it can be concluded that PCA outperforms LDA in case of noisy data. © 2014, Indian Society of Remote Sensing.


Sharma A.M.,Center for and Robotics | Venkatesh K.S.,Indian Institute of Technology Kanpur | Mukerjee A.,Indian Institute of Technology Kanpur
ICIIP 2011 - Proceedings: 2011 International Conference on Image Information Processing | Year: 2011

Human pose estimation from monocular image sequences is attracting increasing attention, and 2D (image-based) as well as 3D (joint-motion based) approaches have been proposed. The former is computationally fast, and works also for less frequent poses, but reliability is low. The latter is computationally expensive owing to the high-dimensionality of the problem, despite attempts at dimensionality-reduction. We propose to impose temporal continuity constraints on the 2D approaches in order to improve reliability and obtain spatio-temporal descriptions of the action in the image plane. In the first stage, at each frame-level spatial localisation will be done by applying background subtraction, after that static image pose estimation is performed using CRF-based probabilistic assembly of parts, based on the approach by Ramanan [1]. Next, pose continuity is imposed via first-order Markovian constraints on the CRF search. This results in improved spatial accuracy as well as significantly reduced search. We present results from the Weizmann video dataset to demonstrate how such an approach can serve as an image-plane based alternative to full 3D modeling or manifold search. © 2011 IEEE.


Suri N.N.R.R.,Center for and Robotics | Murty M.N.,Indian Institute of Science | Athithan G.,Center for and Robotics
Proceedings of the 2012 12th International Conference on Hybrid Intelligent Systems, HIS 2012 | Year: 2012

The rapid growth in the field of data mining has lead to the development of various methods for outlier detection. Though detection of outliers has been well explored in the context of numerical data, dealing with categorical data is still evolving. In this paper, we propose a two-phase algorithm for detecting outliers in categorical data based on a novel definition of outliers. In the first phase, this algorithm explores a clustering of the given data, followed by the ranking phase for determining the set of most likely outliers. The proposed algorithm is expected to perform better as it can identify different types of outliers, employing two independent ranking schemes based on the attribute value frequencies and the inherent clustering structure in the given data. Unlike some existing methods, the computational complexity of this algorithm is not affected by the number of outliers to be detected. The efficacy of this algorithm is demonstrated through experiments on various public domain categorical data sets. © 2012 IEEE.


Faheema A.G.,Center for and Robotics | Rakshit S.,Center for and Robotics
2010 IEEE 2nd International Advance Computing Conference, IACC 2010 | Year: 2010

In this paper, we introduce an efficient method to substantially increase the recognition performance of object recognition by employing feature selection method using bag-of-visual-word representation. The proposed method generates visual vocabulary from a large set of images using visual vocabulary tree. Images are represented by a vector of weighted word frequencies. We have introduced on-line feature selection method, which for a given query image selects the relevant features from a large weighted word vector. The learned database image vectors are also reduced using the selected features. This will improve the classification accuracy and also reduce the overall computational complexity by dimensionality reduction of the classification problem. In addition, it will help us in discarding the irrelevant features, which if selected will deteriorate the classification results. We have demonstrated the efficiency our method on the Caltech dataset. ©2010 IEEE.


Suri N.N.R.R.,Center for and Robotics | Murty M.N.,Indian Institute of Science | Athithan G.,Center for and Robotics
Proceedings of the 2012 12th International Conference on Hybrid Intelligent Systems, HIS 2012 | Year: 2012

Outlier detection in high dimensional categorical data has been a problem of much interest due to the extensive use of qualitative features for describing the data across various application areas. Though there exist various established methods for dealing with the dimensionality aspect through feature selection on numerical data, the categorical domain is actively being explored. As outlier detection is generally considered as an unsupervised learning problem due to lack of knowledge about the nature of various types of outliers, the related feature selection task also needs to be handled in a similar manner. This motivates the need to develop an unsupervised feature selection algorithm for efficient detection of outliers in categorical data. Addressing this aspect, we propose a novel feature selection algorithm based on the mutual information measure and the entropy computation. The redundancy among the features is characterized using the mutual information measure for identifying a suitable feature subset with less redundancy. The performance of the proposed algorithm in comparison with the information gain based feature selection shows its effectiveness for outlier detection. The efficacy of the proposed algorithm is demonstrated on various high-dimensional benchmark data sets employing two existing outlier detection methods. © 2012 IEEE.


Singh S.,Center for and Robotics | Krishna K.M.,Indian Institute of Technology Hyderabad
Proceedings of the IEEE International Conference on Control Applications | Year: 2013

In this paper we develop an algorithm to generate gait sequences to negotiate a discontinuous terrain for a hybrid 4-wheeled legged robot. The gait sequence comprises two main steps - normal force redistribution and hybrid position-force control. The robot climbs the discontinuity one leg at a time. This requires that the entire load of the robot is taken up by the other three legs so that the leg climbing the discontinuity is free. For this purpose a load redistribution methodology is used which makes the center of gravity of chassis coincide with the desired center of pressure (CoP). Subsequently the free leg moves in hybrid position and force control to climb the discontinuity. Force sensing ensures constant contact with the terrain and detection of stand and end of the discontinuity without using any perception sensor. The methodology is validated using multi-body dynamic simulation. © 2013 IEEE.


Ravi V.C.,Center for and Robotics | Rakshit S.,Center for and Robotics | Ghosal A.,Indian Institute of Science
Journal of Mechanisms and Robotics | Year: 2010

Hyper-redundant robots are characterized by the presence of a large number of actuated joints, a lot more than the number required to perform a given task. These robots have been proposed and used for many applications involving avoiding obstacles or, in general, to provide enhanced dexterity in performing tasks. Making effective use of the extra degrees-of-freedom or resolution of redundancy has been an extensive topic of research and several methods have been proposed in literature. In this paper, we compare three known methods and show that an algorithm based on a classical curve, called the tractrix, leads to a more "natural" motion of the hyper-redundant robot with the displacements diminishing from the end-effector to the fixed base. In addition, since the actuators nearer the base "see" a greater inertia due to the links farther away, smaller motion of the actuators nearer the base results in better motion of the end-effector as compared with other two approaches. We present simulation and experimental results performed on a prototype eight-link planar hyper-redundant manipulator. © 2010 by ASME.


Singh S.,Center for and Robotics | Jadhav B.D.,Center for and Robotics | Krishna K.M.,Indian Institute of Technology Hyderabad
Proceedings - IEEE International Conference on Robotics and Automation | Year: 2014

In this paper, we present a posture control scheme for step climbing by an in-house developed three-segmented tracked robot, miniUGV. The posture control scheme results in minimum torque at the actuated joints of the segments. Non-linear optimization is carried out offline for progressively decreasing distance of the robot from the step with torque minimization as objective function and force balance, motor torque limits, slippage avoidance and interference avoidance constraints. The resulting angles of the joints are fitted to a third degree polynomial as a function of the robot distance from the step and the step height. It is shown that a single set of polynomial functions is sufficient for climbing steps of all permissible heights and angles of attack of the front segment. The methodology has been verified through simulation followed by implementation on the real robot. As a consequence of this optimization we find that the average current reduced by more than thirty percent, reducing power consumption and confirming the efficacy of the optimization framework. © 2014 IEEE.

Loading Center for and Robotics collaborators
Loading Center for and Robotics collaborators