Nikhil Somani

Nikhil Somani

Auto-generated profile, based on publicly available information

Nikhil Somani

Fortiss GmbH, An-Institut Technische Universität München, Munich, Germany

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
4 January 2019 in IEEE Robotics & Automation Magazine
Verified
Journal Article
Open access
APAlexander Perzylo
Alexander Perzylo
MRMarkus Rickert
Markus Rickert
BKBjorn Kahl
Bjorn Kahl
NSNikhil Somani
Nikhil Somani
CLChristian Lehmann
Christian Lehmann
MDMarinus Danzer
Marinus Danzer

1 December 2014
Verified
Conference Paper
Closed access
ARAlina Roitberg
Alina Roitberg
APAlexander Perzylo
Alexander Perzylo
NSNikhil Somani
Nikhil Somani
MGManuel Giuliani
Manuel Giuliani
MRMarkus Rickert
Markus Rickert
AKAlois Knoll
Alois Knoll
Human activity recognition is crucial for intuitive cooperation between humans and robots. We present an approach for activity recognition for applications in the context of human-robot interaction in industrial settings. The approach is based on spatial and temporal features derived from skeletal data of human workers performing assembly tasks. These features were used to train a machine learning framework, which classifies discrete time frames with Random Forests and subsequently models temporal dependencies between the resulting states with a Hidden Markov Model. We considered the following three groups of activities: Movement, Gestures, and Object handling. A dataset has been collected which is comprised of 24 recordings of several human workers performing such activities in a human-robot interaction environment, as typically seen at small and medium-sized enterprises. The evaluation shows that the approach achieves a recognition accuracy of up to 88% for some activities and an average accuracy of 73%.

9 November 2015
Verified
Conference Paper
Open access
ARAlina Roitberg
Alina Roitberg
NSNikhil Somani
Nikhil Somani
APAlexander Perzylo
Alexander Perzylo
MRMarkus Rickert
Markus Rickert
AKAlois Knoll
Alois Knoll
We present an approach for monitoring and interpreting human activities based on a novel multimodal vision-based interface, aiming at improving the efficiency of human-robot interaction (HRI) in industrial environments. Multi-modality is an important concept in this design, where we combine inputs from several state-of-the-art sensors to provide a variety of information, e.g. skeleton and fingertip poses. Based on typical industrial workflows, we derived multiple levels of human activity labels, including large-scale activities (e.g. assembly) and simpler sub-activities (e.g. hand gestures), creating a duration- and complexity-based hierarchy. We train supervised generative classifiers for each activity level and combine the output of this stage with a trained Hierarchical Hidden Markov Model (HHMM), which models not only the temporal aspects between the activities on the same level, but also the hierarchical relationships between the levels.

1 September 2015
Verified
Conference Paper
Closed access
APAlexander Perzylo
Alexander Perzylo
NSNikhil Somani
Nikhil Somani
MRMarkus Rickert
Markus Rickert
AKAlois Knoll
Alois Knoll
In this paper, we introduce an approach for leveraging CAD description to a semantic level, in order to link additional knowledge to CAD models and to exploit resulting synergy effects. This has been achieved by designing a description language, based on the Web Ontology Language (OWL), that is used to define boundary representations (BREP) of objects. This involves representing geometric entities in a semantic meaningful way, e.g., a circle is defined by a coordinate frame and a radius instead of a set of polygons. Furthermore, the scope of this semantic description language also covers geometric constraints between multiple objects. Constraints can be specified not only on the object level, but down to single edges or faces of an object. This semantic representation is used to improve a variety of applications, ranging from shape-based object recognition to constraint-based robot task descriptions. Results from a quantitative evaluation are presented to assess the practicability of this approach.

1 October 2016
Verified
Conference Paper
Closed access
APAlexander Perzylo
Alexander Perzylo
NSNikhil Somani
Nikhil Somani
SPStefan Profanter
Stefan Profanter
IKIngmar Kessler
Ingmar Kessler
MRMarkus Rickert
Markus Rickert
AKAlois Knoll
Alois Knoll
In this paper, we introduce a novel robot programming paradigm. It focuses on reducing the required expertise in robotics to a level that allows shop floor workers to use robots in their application domain without the need of extensive training. Our approach is user-centric and can interpret underspecified robot tasks, enabling communication on an abstract level. Such high-level task descriptions make the system amenable for users that are experts in a particular domain, but have limited knowledge about robotics and are thus not able to specify low-level details and instructions. Semantic models for all involved entities, i.e., processes, workpieces, and workcells, enable automatic reasoning about underspecified tasks and missing pieces of information. We showcase and evaluate this methodology on two industrial use cases from the domains of assembly and woodworking, comparing it to state-of-the-art solutions provided by robot manufacturers.

30 March 2016 in IEEE Transactions on Robotics
Verified
Journal Article
Closed access
CCCaixia Cai
Caixia Cai
NSNikhil Somani
Nikhil Somani
AKAlois Knoll
Alois Knoll
We present an approach to control a 6-degree-of-freedom (DOF) manipulator using an uncalibrated visual servoing (VS) approach that addresses the challenges of choosing proper image features for target objects and designing a VS controller to enhance the tracking performance. The main contribution of this paper is the definition of a new virtual visual space (image space). A novel stereo camera model employing virtual orthogonal cameras is used to map 6-D poses from Cartesian space to this virtual visual space. Each component of the 6-D pose vector defined in this virtual visual space is linearly independent, leading to a full-rank 6 × 6 image Jacobian matrix, which allows avoiding classical problems, such as image space singularities and local minima. Furthermore, the control for rotational and translational motion of robot is decoupled due to the diagonal image Jacobian. Finally, simulation results with an eye-to-hand robotic system confirm the improvement in controller stability and motion performance with respect to conventional VS approaches. Experimental results on a 6-DOF industrial robot are provided to illustrate the effectiveness of the proposed method and the feasibility of using this method in practical scenarios.