Selected Publications

In the era of Internet of Things, there is an increasing demand for networked computing to support the requirements of timeconstrained, compute-intensive distributed applications. We present a container orchestration architecture for dispersed computing, and its implementation in an open source software called Jupiter. The system automates the distribution of computational tasks for complex computational applications described as an Directed Acyclic Graph (DAG) to efficiently distribute the tasks among a set of networked compute nodes and orchestrates the execution of the DAG thereafter. This Kubernetes based container-orchestration system supports both centralized and decentralized scheduling algorithms for optimally mapping the tasks based on information from a range of profilers: network profilers, resource profilers, and execution time profilers.
In WOC, Middleware, 2019.

Detecting activities from video taken with a single camera is an active research area for ML-based machine vision. In this paper, we examine the next research frontier: near real-time detection of complex activities spanning multiple (possibly wireless) cameras, a capability applicable to surveillance tasks. We argue that a system for such complex activity detection must employ a hybrid design: one in which rule-based activity detection must complement neural network based detection. Moreover, to be practical, such a system must scale well to multiple cameras and have low end-to-end latency. Caesar, our edge computing based system for complex activity detection, provides an extensible vocabulary of activities to allow users to specify complex actions in terms of spatial and temporal relationships between actors, objects, and activities. Caesar converts these specifications to graphs, efficiently monitors camera feeds, partitions processing between cameras and the edge cluster, retrieves minimal information from cameras, carefully schedules neural network invocation, and efficiently matches specification graphs to the underlying data in order to detect complex activities. Our evaluations show that Caesar can reduce wireless bandwidth, on-board camera memory, and detection latency by an order of magnitude while achieving good precision and recall for all complex activities on a public multi-camera dataset.
In Sensys, 2019.

We present Autonomous Rssi based RElative poSitioning and Tracking (ARREST), a new robotic sensing system for tracking and following a moving, RF-emitting object, which we refer to as the Leader, solely based on signal strength information. Our proposed tracking agent, which we refer to as the TrackBot, uses a single rotating, off-the-shelf, directional antenna, novel angle and relative speed estimation algorithms, and Kalman filtering to continually estimate the relative position of the Leader with decimeter level accuracy (which is comparable to a state-of-the-art multiple access point based RF-localization system) and the relative speed of the Leader with accuracy on the order of 1 m/s. The TrackBot feeds the relative position and speed estimates into a Linear Quadratic Gaussian (LQG) controller to generate a set of control outputs to control the orientation and the movement of the TrackBot. We perform an extensive set of real world experiments with a full-fledged prototype to demonstrate that the TrackBot is able to stay within 5m of the Leader with: (1) more than 99% probability in line of sight scenarios, and (2) more than 75% probability in no line of sight scenarios, when it moves 1.8X faster than the Leader.
In IEEE TMC, 2019.

We present the Intelligent Robotic IoT System (IRIS), a modular, portable, scalable, and open-source testbed for robotic wireless network research. There are two key features that separate IRIS from most of the state-of-the-art multi-robot testbeds. (1) Portability: IRIS does not require a costly static global positioning system such as a VICON system nor time-intensive vision-based SLAM for its operation. Designed with an inexpensive Time Difference of Arrival (TDoA) localization system with centimeter level accuracy, the IRIS testbed can be deployed in an arbitrary uncontrolled environment in a matter of minutes. (2) Programmable Wireless Communication Stack: IRIS comes with a modular programmable low-power IEEE 802.15.4 radio and IPv6 network stack on each node. For the ease of administrative control and communication, we also developed a lightweight publish-subscribe overlay protocol called ROMANO that is used for bootstrapping the robots (also referred to as the IRISbots), collecting statistics, and direct control of individual robots, if needed. We detail the modular architecture of the IRIS testbed design along with the system implementation details and localization performance statistics.
In IROS, 2018.

Recent Publications

More Publications

. Container Orchestration for Dispersed Computing. In WOC, Middleware, 2019.

Details PDF Code Project

. Caesar: cross-camera complex activity recognition. In Sensys, 2019.

Details PDF Code Project

. Robotic Wireless Sensor Networks. In Mission-Oriented Sensor Networks and Systems: Art and Science, Springer, 2019.

Details PDF Project

. ARREST: A RSSI Based Approach for Mobile Sensing and Tracking of a Moving Object. In IEEE TMC, 2019.

Details PDF Video Project

. Intelligent Robotic IoT System (IRIS) Testbed. In IROS, 2018.

Details Video Code Project

. Thesis: Relative Positioning, Network Formation, and Routing in Robotic Wireless Networks. University of Southern California, 2018.

Details PDF Project

. WAVE: A Distributed Scheduling Framework for Dispersed Computing. USC ANRG Technical Report, ANRG-2018-01, 2018.

Details PDF Code Project

. End-to-End Network Performance Monitoring for Dispersed Computing. In ICNC’18, 2018.

Details Code Project

. ARREST: A RSSI Based Approach for Mobile Sensing and Tracking of a Moving Object. In WiUAV (GLOBECOM), 2017.

Details Video Project

. Empirical Evaluation of the Heat-Diffusion Collection Protocol for Wireless Sensor Networks. In COMNET, 2017.

Details PDF Project

Recent & Upcoming Talks

miniRadar: A Low Power IEEE 802.15.4 Transceiver Based Implementation of Bistatic Radar

Feb 14, 2018, Information Theory and Applications Workshop 2018 (Invited Poster)

MHI Pitch: Relative Positioning and Network Formation in Robotic Wireless Networks

Nov 10, 2017, USC MHI Research Festival 2017 (Best Pitch Award)

Awards and Honors

  • Received the Best Graduating PhD Student Pitch award at MHI Research Festival 2017
  • Research Proposal was accepted in the NeTS Early Career Workshop 2017
  • Selected as one of the five MHI Scholars. Only 4-5 students are selected from a competitive process each year from the department
  • Research was featured in USC News (https://news.usc.edu/88394/can-robots-come-to-the-rescue-in-a-burning-building/)
  • Accepted for USC Doctoral Student Summer Institute, a program administered by the USC Graduate School, Academic Professional Development (APD) & Enhancing Diversity in Graduate Education (EDGE) with summer funding.
  • Accepted for Ph.D program at USC with USC Provost’s Fellowship
  • Ranked 55th (General) in Engineering in WBJEE (2008) among about 1,00,000 students.
  • Ranked 168th (General) in Medical in WBJEE (2008) among about 60,000 students

Teaching

I have been a teaching assistant for the following courses at University of Southern California:

  • EE 109: Introduction to Embedded Systems (Spring 2017, Fall 2017)
  • EE 597: Wireless and Mobile Networks Design and Laboratory (Spring 2016)
  • EE 450: Computer Networks (Fall 2014, Spring 2015, Fall 2016)

Contact

  • pradiptg@usc.edu
  • SAL 227, University of Southern California, Los Angeles California, 90089, USA
  • Email for appointment