Sharath Chandra Akkaladevi

Sharath Chandra Akkaladevi

Auto-generated profile, based on publicly available information

Sharath Chandra Akkaladevi

PROFACTOR GmbH

Research Focus & Metrics

Academic Career Length

14Years (2013-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2017 in Procedia Manufacturing
Verified
Journal Article
Open access
APAndreas Pichler
Andreas Pichler
SASharath Chandra Akkaladevi
Sharath Chandra Akkaladevi
MIMarkus Ikeda
Markus Ikeda
MHMichael Hofmann
Michael Hofmann
MPMatthias Plasch
Matthias Plasch
GFGerald Fritz
Gerald Fritz

1 November 2015
Verified
Conference Paper
Closed access
SASharath Chandra Akkaladevi
Sharath Chandra Akkaladevi
CHChristoph Heindl
Christoph Heindl
Human action recognition plays a vital role in the field of human-robot interaction and is widely researched for its potential applications. In this paper we propose a human action recognition framework for human robot interaction in industrial applications. First, a set of key descriptors are learned from a collection of weak spatio-temporal skeletal joint descriptors using random forests, which reduces the dimensionality and computational effort. We show that our approach reduces the descriptor dimensionality by 61 percent. The key descriptors are used with a multi-label one-versus-all binary random forest classifier for action classification. We propose an extension to the framework that allows recognizing multiple actions for a given time instant. This results in a low latency, flexible and re-configurable method that performs on par with other sophisticated approaches on challenging benchmarks like the MSR Action 3D dataset.

22 November 2018 in Frontiers in Robotics and AI
Verified
Journal Article
Open access
PDF file
SASharath Chandra Akkaladevi
Sharath Chandra Akkaladevi
MPMatthias Plasch
Matthias Plasch
SMSriniwas Maddukuri
Sriniwas Maddukuri
CEChristian Eitzinger
Christian Eitzinger
APAndreas Pichler
Andreas Pichler
BRBernhard Rinner
Bernhard Rinner
As manufacturing demographics change from mass production to mass customization, advances in human-robot interaction in industries have taken many forms. However, the topic of reducing the programming effort required by an expert using natural modes of communication is still open. To answer this challenge, we propose an approach based on Interactive Reinforcement Learning that learns a complete collaborative assembly process. The learning approach is done in two steps. First step consists of modeling simple tasks that compose the assembly process, using task based formalism. The robotic system then uses these modeled simple tasks and proposes to the user a set of possible actions at each step of the assembly process via a GUI. The user then “interacts” with the robotic system by selecting an option from the given choice. The robot records the action chosen and performs it, progressing the assembly process. Thereby, the user teaches the system which task to perform when. In order to reduce the number of actions proposed, the system considers additional information such as user and robot capabilities and object affordances. These set of action proposals are further reduced by modeling the proposed actions into a goal based hierarchy and by including action prerequisites. The learning framework highlights its ability to learn a complicated human robot collaborative assembly process in a user intuitive fashion. The framework also allows different users to teach different assembly processes to the robot.

31 October 2019 in e+i Elektrotechnik und Informationstechnik
Verified
Journal Article
Closed access
PDF file
SASharath Chandra Akkaladevi
Sharath Chandra Akkaladevi
APAndreas Pichler
Andreas Pichler
MPMatthias Plasch
Matthias Plasch
MIMarkus Ikeda
Markus Ikeda
MHMichael Hofmann
Michael Hofmann

1 May 2016
Verified
Conference Paper
Closed access
SASharath Akkaladevi
Sharath Akkaladevi
MAMartin Ankerl
Martin Ankerl
CHChristoph Heindl
Christoph Heindl
APAndreas Pichler
Andreas Pichler
In this paper, a robust, real-time object tracking approach capable of dealing with multiple symmetric and non-symmetric objects in a real-time requirement setting is proposed. The approach relies only on depth data to track multiple objects in a dynamic environment and uses random-forest based learning to deal with problems like object occlusion, motion-blur due to camera motion and clutter. We show that the relation between object motion and the corresponding change in its 3D point cloud data can be learned using only 6 random forests. A framework that unites object pose estimation and object pose tracking to efficiently track multiple objects in 3D space is presented. The approach is robust in tracking objects even in presence of motion blur that causes noisy depth data and is capable of real-time performance with 1.8ms per frame. The experimental evaluations demonstrate the performance of the approach against robustness, accuracy and speed and compare the approach with the state of the art. A publicly available dataset with real-world data is also provided for future benchmarking.

4 April 2016 in Autonomous Robots
Verified
Journal Article
Closed access
PDF file
ABAjaz Ahmad Bhat
Ajaz Ahmad Bhat
SASharath Chandra Akkaladevi
Sharath Chandra Akkaladevi
VMVishwanathan Mohan
Vishwanathan Mohan
Christian EitzingerChristian Eitzinger
Christian Eitzinger
PMPietro Morasso
Pietro Morasso