Chayan Sarkar
TCS Innovation labs, Robotics & Autonomous Systems, Department Member
- Chayan Sarkar is a Scientist at the TCS Research. He received his bachelor’s and master’s degree in Computer Science ... moreChayan Sarkar is a Scientist at the TCS Research. He received his bachelor’s and master’s degree in Computer Science from Jadavpur University in 2009 and IIT Bombay in 2011, respectively. He completed his doctoral studies at the Delft University of Technology, the Netherlands in 2016. He briefly worked as a post-doctoral scholar at SICS Swedish ICT in Sweden. Currently, he is part of the embedded systems and robotics research area of TCS Research. His research interest includes the Internet of Things, Embedded Systems, Multi-robot systems, and Human-robot interactions.edit
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
We have developed a robotics ontology, OntoScene, that extends IEEE CORA [5] and SemNav [1] ontologies. Contrary to the prior work that lacked usage of ontology in scene understanding, the proposed system uses OntoScene to figure out... more
We have developed a robotics ontology, OntoScene, that extends IEEE CORA [5] and SemNav [1] ontologies. Contrary to the prior work that lacked usage of ontology in scene understanding, the proposed system uses OntoScene to figure out objects and their relations in a scene and create a scene graph for aid in various cognitive robotic tasks where object localization, scene graph generation is important. This work positions semantic web technology as a key enabler in robotic tasks.
Research Interests:
Research Interests:
Research Interests:
As the number of robots in our daily surroundings like home, office, restaurants, factory floors, etc. are increasing rapidly, the development of natural human-robot interaction mechanism becomes more vital as it dictates the usability... more
As the number of robots in our daily surroundings like home, office, restaurants, factory floors, etc. are increasing rapidly, the development of natural human-robot interaction mechanism becomes more vital as it dictates the usability and acceptability of the robots. One of the valued features of such a cohabitant robot is that it performs tasks that are instructed in natural language. However, it is not trivial to execute the human intended tasks as natural language expressions can have large linguistic variations. Existing works assume either single task instruction is given to the robot at a time or there are multiple independent tasks in an instruction. However, complex task instructions composed of multiple inter-dependent tasks are not handled efficiently in the literature. There can be ordering dependency among the tasks, i.e., the tasks have to be executed in a certain order or there can be execution dependency, i.e., input parameter or execution of a task depends on the ou...
Research Interests:
An efficient communication mechanism forms the backbone for any multi-robot system to achieve fruitful collaboration and coordination. Limitation in the existing asynchronous transmission based strategies in fast dissemination and... more
An efficient communication mechanism forms the backbone for any multi-robot system to achieve fruitful collaboration and coordination. Limitation in the existing asynchronous transmission based strategies in fast dissemination and aggregation compels the designers to prune down such requirements as much as possible. This also restricts the possible application areas of mobile multi-robot systems. In this work, we introduce concurrent transmission based strategy as an alternative. Despite the commonly found difficulties in concurrent transmission such as microsecond level time synchronization, hardware heterogeneity, etc., we demonstrate how it can be exploited for multi-robot systems. We propose a split architecture where the two major activities - communication and computation are carried out independently and coordinate through periodic interactions. The proposed split architecture is applied on a custom-built, fully networked control system consisting of five two-wheel differenti...
Research Interests:
In this article, we propose an energy-efficient data gathering scheme for wireless sensor network called Sleep-Route, which splits the sensor nodes into two sets - active and dormant (low-power sleep). Only the active set of sensor nodes... more
In this article, we propose an energy-efficient data gathering scheme for wireless sensor network called Sleep-Route, which splits the sensor nodes into two sets - active and dormant (low-power sleep). Only the active set of sensor nodes participate in data collection. The sensing values of the dormant sensor nodes are predicted with the help of an active sensor node. Virtual Sensing Framework (VSF) provides the mechanism to predict the sensing values by exploiting the data correlation among the sensor nodes. If the number of active sensor nodes can be minimized, a lot of energy can be saved. The active nodes' selection must fulfill the following constraints - (i) the set of active nodes are sufficient to predict the sensing values of the dormant nodes, (ii) each active sensor nodes can report their data to the sink node (directly or through some other active node(s)). The goal is to select a minimal number of active sensor nodes so that energy savings can be maximized. The opti...
Robots in our daily surroundings are increasing day by day. Their usability and acceptability largely depend on their explicit and implicit interaction capability with fellow human beings. As a result, social behavior is one of the most... more
Robots in our daily surroundings are increasing day by day. Their usability and acceptability largely depend on their explicit and implicit interaction capability with fellow human beings. As a result, social behavior is one of the most sought-after qualities that a robot can possess. However, there is no specific aspect and/or feature that defines socially acceptable behavior and it largely depends on the situation, application, and society. In this article, we investigate one such social behavior for collocated robots. Imagine a group of people is interacting with each other and we want to join the group. We as human beings do it in a socially acceptable manner, i.e., within the group, we do position ourselves in such a way that we can participate in the group activity without disturbing/obstructing anybody. To possess such a quality, first, a robot needs to determine the formation of the group and then determine a position for itself, which we humans do implicitly. The theory of ...
Research Interests:
The low-power wireless bus (LWB) is a highly efficient communication protocol for wireless sensor networks (WSN). However, a lack of open implementation for this protocol prompted the implementation of the protocol for the most common... more
The low-power wireless bus (LWB) is a highly efficient communication protocol for wireless sensor networks (WSN). However, a lack of open implementation for this protocol prompted the implementation of the protocol for the most common platform of WSN related research, the sky nodes using the Contiki operating system. This document provides the detailed description of the implementation. A forwarder-selection mechanism is developed to improve energy-efficiency of LWB in data collection scenario. The implementation also consists the forwarder selection mechanism. One can either use the original features of LWB or enforce the forwarder selection mechanism.
Research Interests:
Recently occupancy-based lighting control has shown a great promise towards achieving better energy efficiency. Generally, traditional systems use additional sensors to detect user presence with higher precision to better the control... more
Recently occupancy-based lighting control has shown a great promise towards achieving better energy efficiency. Generally, traditional systems use additional sensors to detect user presence with higher precision to better the control algorithms. In this work, we show how a smartphone-based indoor localization can be utilized for this purpose without deploying additional sensors. Apart from automatic controlling of the lights, our system provides a sophisticated manual control, where each light unit can be controlled by just pointing the phone towards it. Based on our experiments, we show that up to 67% more energy saving is possible using our systems compared to traditional methods.
Research Interests:
Wireless sensor networks (WSNs) have enabled continuous monitoring of an area of interest (body, room, region, etc.) while eliminating expensive wired infrastructure. Typically in such applications, wireless sensor nodes report the sensed... more
Wireless sensor networks (WSNs) have enabled continuous monitoring of an area of interest (body, room, region, etc.) while eliminating expensive wired infrastructure. Typically in such applications, wireless sensor nodes report the sensed values to a sink node, where the information is required for the end-user. WSNs also provide the flexibility to the end-user for choosing several parameters for the monitoring application. For example, placement of sensors, frequency of sensing and transmission of those sensed data. Over the years, the advancement in embedded technology has led to increased processing power and memory capacity of these battery powered devices. However, batteries can only supply limited energy, thus limiting the lifetime of the network. In order to prolong the lifetime of the deployment, various efforts have been made to improve the battery technologies and also reduce the energy consumption of the sensor node at various layers in the networking stack. Of all the op...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
This paper presents a novel architecture to detect social groups in real-time from a continuous image stream of an ego-vision camera. F-formation defines social orientations in space where two or more person tends to communicate in a... more
This paper presents a novel architecture to detect social groups in real-time from a continuous image stream of an ego-vision camera. F-formation defines social orientations in space where two or more person tends to communicate in a social place. Thus, essentially, we detect F-formations in social gatherings such as meetings, discussions, etc. and predict the robot’s approach angle if it wants to join the social group. Additionally, we also detect outliers, i.e., the persons who are not part of the group under consideration. Our proposed pipeline consists of – a) a skeletal key points estimator (a total of 17) for the detected human in the scene, b) a learning model (using a feature vector based on the skeletal points) using CRF to detect groups of people and outlier person in a scene, and c) a separate learning model using a multi-class Support Vector Machine (SVM) to predict the exact F-formation of the group of people in the current scene and the angle of approach for the viewin...
Research Interests: Computer Science and IEEE
Research Interests:
The low-power wireless bus (LWB) is a highly efficient communication protocol for wireless sensor networks (WSN). However, a lack of open implementation for this protocol prompted the implementation of the protocol for the most common... more
The low-power wireless bus (LWB) is a highly efficient communication protocol for wireless sensor networks (WSN). However, a lack of open implementation for this protocol prompted the implementation of the protocol for the most common platform of WSN related research, the sky nodes using the Contiki operating system. This document provides the detailed description of the implementation. A forwarder-selection mechanism is developed to improve energy-efficiency of LWB in data collection scenario. The implementation also consists the forwarder selection mechanism. One can either use the original features of LWB or enforce the forwarder selection mechanism.
Research Interests:
Using a robotic platform for telepresence applications has gained paramount importance in this decade. Scenarios such as remote meetings, group discussions, and presentations/talks in seminars and conferences get much attention in this... more
Using a robotic platform for telepresence applications has gained paramount importance in this decade. Scenarios such as remote meetings, group discussions, and presentations/talks in seminars and conferences get much attention in this regard. Though there exist some robotic platforms for such telepresence applications, they lack efficacy in communication and interaction between the remote person and the avatar robot deployed in another geographic location. Also, such existing systems are often cloud-centric which adds to its network overhead woes. In this demo, we develop and test a framework that brings the best of both cloud and edge-centric systems together along with a newly designed communication protocol. Our solution adds to the improvement of the existing systems in terms of robustness and efficacy in communication for a geographically distributed environment.
Research Interests:
Research Interests: Computer Science and IEEE
With the advent of Industry 4.0 era, employing a team of robots within a factory floor or a warehouse is pretty prevalent today as robots can perform a known task with higher accuracy and efficiency if its capability permits. Efficiency... more
With the advent of Industry 4.0 era, employing a team of robots within a factory floor or a warehouse is pretty prevalent today as robots can perform a known task with higher accuracy and efficiency if its capability permits. Efficiency and throughput of such a setup depend on careful task assignment and scheduling, which further depend on utility calculation. Though there exists a number of techniques to perform efficient task allocation, they assume the utility values are available and static. They neither consider all the relevant parameters nor the dynamic changes that may occur during task execution. Moreover, methods of automating such dynamic utility calculation (both at the start and at runtime) based on knowledge and semantics are not present and this is a hindrance to building a fully automated robotic workforce. In this article, we explore an avenue of semantic-based dynamic utility calculation and showcase its application for a use-case.
Research Interests:
Computers were invented to automate the labour-intensive computing process. The advancement of semiconductor technology has reduced the form-factor and cost of computers, and increased their usability. This has gradually introduced... more
Computers were invented to automate the labour-intensive computing process. The advancement of semiconductor technology has reduced the form-factor and cost of computers, and increased their usability. This has gradually introduced computers in various control and automation systems. The further rise of miniatuarized computing devices paves the way for autonomous monitoring using embedded devices. In the last two decades, we observed a huge surge of such monitoring and control systems. These systems are generally termed as the wireless sensor and actuator networks (WSAN). In a WSAN, a number of sensor nodes monitors a deployment area where data collection by humans is either difficult or costly. These devices collaboratively report their sensor readings to a centralized node called the sink. The sink is connected with the Internet, thus delivers the data to the outside world. This way the deployment region can be monitored remotely. Similarly, some actuators can also be controlled r...
Research Interests:
Multi-robot systems are deployed in a warehouse to automate the process of storing and retrieving objects in and out of the warehouse. The efficiency of the system largely depends on how the tasks are allocated to the robots. Though there... more
Multi-robot systems are deployed in a warehouse to automate the process of storing and retrieving objects in and out of the warehouse. The efficiency of the system largely depends on how the tasks are allocated to the robots. Though there exists a number of techniques that can perform multi-robot task allocation quite efficiently, they hardly consider deadline for task completion while assigning tasks to the robots. A careful allocation is of paramount importance when there is an associated penalty with each of the tasks if it is not completed within a stipulated time. In this work, we develop an algorithm, called Minimum Penalty Scheduling (MPS) that allocates tasks among a group of robots with the goal that the overall penalty of executing all the tasks can be minimized. Our algorithm provides a robust, scalable, and near-optimal real-time task schedule. By comparing with the state-of-the-art algorithm, we show that MPS attracts up to 62.5% less penalty when a significant number o...
Research Interests:
Research Interests:
In smartcard-based travel payment systems, passengers have to place the smartcard near the journey registration devices once each for check-in and check-out to authenticate their travel. This is an annoying process when if the journey... more
In smartcard-based travel payment systems, passengers have to place the smartcard near the journey registration devices once each for check-in and check-out to authenticate their travel. This is an annoying process when if the journey involves multiple stops. In this paper, we describe a working system of secure energy-efficient automatic ticketing (SEAT) for public transport, which transforms traditional check-in/check-out system into Be-in/Be-out system. In SEAT, a Bluetooth low energy (BLE) enabled smartphone communicates with registration devices to track the journey for pricing without any human intervention. SEAT is vigilant toward the energy consumption of the BLE device under various conditions, and security and privacy threats to the overall ecosystem. We develop models for energy consumption and latency for BLE devices under the influence of mutual interference based on experiments with 32 BLE devices. We utilize these models to develop an energy-efficient protocol for SEAT that is secure and privacy preserving. Our experiments show that a BLE module consumes only 18.3 J daily under the proposed system model, which is less than 0.1% of the total capacity of a typical smartphone battery.
Research Interests:
Research Interests:
The constructive interference (CI) phenomenon has been exploited by a number of protocols for providing energy-efficient, low-latency, and reliable data collection and dissemination services in wireless sensor networks. These protocols... more
The constructive interference (CI) phenomenon has been exploited by a number of protocols for providing energy-efficient, low-latency, and reliable data collection and dissemination services in wireless sensor networks. These protocols consider CI to provide highly reliable packet delivery. This has attracted attention to understand the working of CI; however, the existing works present inconsistent views. Furthermore, these works do not study in the real-world settings where the physical conditions of deployment and unreliable wireless channels also impact the performance of CI. Therefore, we study the phenomenon of CI, considering a receiver’s viewpoint and analyze the parameters that affect CI. We validate our arguments with results from extensive and rigorous experimentation in real-world settings. This paper presents comprehensive insights into the CI phenomenon. With the understanding, we develop the destructive interference-based power adaptation (DIPA), an energy-efficient and distributed algorithm, that adapts transmission power to improve the performance of CI. Since CI-based protocols cannot have an explicit acknowledgment packet, we make use of destructive interference on a designated byte to provide a feedback. We leverage this feedback to adapt transmission powers. We compared CI with and without DIPA in two real-life testbeds. On one testbed, we achieve around 25% lower packet losses while using only half of its transmission power for 64-B packets. On the other testbed, we achieve 25% lower packet losses while consuming only 47% of its transmission power for 128-B packets. Existing CI-based protocols can easily incorporate DIPA into them to achieve lower packet losses and higher energy efficiencies.
Research Interests:
For the Internet of Things (IoT) applications that send a few bytes of sensor information infrequently, several long-range IoT technologies have been conceived. Narrowband IoT (NB-IoT) is one of them that stands out due to its extended... more
For the Internet of Things (IoT) applications that send a few bytes of sensor information infrequently, several long-range IoT technologies have been conceived. Narrowband IoT (NB-IoT) is one of them that stands out due to its extended coverage, high penetrability, and high reliability features. Among the primary goals set for the standard, low device power consumption is significant as the devices are typically deployed with batteries. In this paper, we characterize an NB-IoT device with respect to its energy consumption in different coverage classes for various scenarios. Based on the measurements, we estimate the lifetime of the device. We find that the lifetime of the device is significantly affected by the coverage class of the device. In order to augment the battery, we investigate the possibility of using ambient energy sources in the context of a smart home. For this we analyze real-world data sets, and find that the harvesting technologies can increase the average lifetime ...
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Research Interests:
Abstract—With the advent of newer technologies and highly miniaturized and computationally capable communicating devices, many possibilities of service provisioning is opening-up. The ICT (Information and Communication Technology) devices... more
Abstract—With the advent of newer technologies and highly miniaturized and computationally capable communicating devices, many possibilities of service provisioning is opening-up. The ICT (Information and Communication Technology) devices are now getting into our everyday life without our notice. Since the needs of a person are different from another and so many different situations have to be dealt with, an exact service could not always be offered. This document offers a solution called an approximate service, ...
Research Interests:
Abstract: This deliverable describes the underlying techniques and tools for the COAST context awareness, network awareness and content adaptation. It describes how COAST utilizes context information to improve network performance and... more
Abstract: This deliverable describes the underlying techniques and tools for the COAST context awareness, network awareness and content adaptation. It describes how COAST utilizes context information to improve network performance and user experience. Out of the general description, a specific example on context detection is described and evaluated via a prototype, which aims to deliver relevant content to the user. The COAST network awareness tools–the ALTO server and active probing methods to estimate the quality of ...
Research Interests:
Telepresence robots are used in various forms in various use-cases that helps to avoid physical human presence at the scene of action. In this work, we focus on a telepresence robot that can be used to attend a meeting remotely with a... more
Telepresence robots are used in various forms in various use-cases that helps to avoid physical human presence at the scene of action. In this work, we focus on a telepresence robot that can be used to attend a meeting remotely with a group of people. Unlike a one-to-one meeting, participants in a group meeting can be located at a different part of the room, especially in an informal setup. As a result, all of them may not be at the viewing angle of the robot, a.k.a. the remote participant. In such a case, to provide a better meeting experience, the robot should localize the speaker and bring the speaker at the center of the viewing angle. Though sound source localization can easily be done using a microphone-array, bringing the speaker or set of speakers at the viewing angle is not a trivial task. First of all, the robot should react only to a human voice, but not to the random noises. Secondly, if there are multiple speakers, to whom the robot should face or should it rotate conti...
Research Interests:
Recently occupancy-based lighting control has shown a great promise towards achieving better energy efficiency. Generally, traditional systems use additional sensors to detect user presence with higher precision to better the control... more
Recently occupancy-based lighting control has shown a great promise towards achieving better energy efficiency. Generally, traditional systems use additional sensors to detect user presence with higher precision to better the control algorithms. In this work, we show how a smartphone-based indoor localization can be utilized for this purpose without deploying additional sensors. Apart from automatic controlling of the lights, our system provides a sophisticated manual control, where each light unit can be controlled by just pointing the phone towards it. Based on our experiments, we show that up to 67% more energy saving is possible using our systems compared to traditional methods.