Charuvahan Adhivarahan

• Multi-robot Simultaneous Localization and Mapping & Sensor Fusion
• Multi-robot planning with Reinforcement Learning

• Charuvahan Adhivarahan and Karthik Dantu, WISDOM: WIreless Sensor-assisted Distributed Online Mapping, 2019 International Conference on Robotics and Automation (ICRA), 2019, pp. 8026-8033
• Zakieh Hashemifar, Charuvahan Adhivarahan, Anand Balakrishnan and Karthik Dantu, Augmenting Visual SLAM with Wi-Fi Sensing For Indoor Applications, Auton Robot, vol. 43, no. 8, pp. 2245–2260, Dec. 2019.
• Zaidd Tasneem, Charuvahan Adhivarahan, Dingkang Wang, Huikai Xie, Karthik Dantu and Sanjeev Koppal, Adaptive Fovea for Scanning Depth Sensors, The International Journal of Robotics Research 39, no. 7 (June 2020): 837–55.
• Charuvahan Adhivarahan and Karthik Dantu, WISDOM: WIreless Sensor-assisted Distributed Online Mapping, The International Journal of Robotics Research (Under Submission).

Solving Multi-Robot Planning Prolems Efficiently by Finding State and Action Abstractions using Reinforcement Learning In-Progress

Multi-robot systems are becoming viable and preferable solutions over monolithic designs in solving complex real-world problems. The benefits of multi-robot systems include modularity, reusability, reconfigurability, customizability and fault tolerance. Multi-robot systems are increasingly becoming popular in several domains, the most important of which are precision agriculture, continuous and sustained patient care and search and rescue operations. The computational complexity in solving these problems are a result of task dependencies in the plan. The scalability issues are typically solved by specialized design choices made by domain experts. We propose a line of research to find and use state and action space abstractions to handle the curse of dimensionality. We propose a combination of formal representations and Reinforcement Learning to achieve this end goal. We believe that the outcome of our research would benefit the research community by providing a platform to study multi-robot and swarm systems planning problems in the context of meta-learning and inductive transfer. Further, we believe that our research will have a broader impact on the society by reducing the time, effort and expertise required to design multi-robot systems solutions for critical applications.

WISDOM: WIreless Sensor-assisted Distributed Online Mapping

Spatial sensing is a fundamental requirement for applications in robotics and augmented reality. In urban spaces such as malls, airports, apartments, and others, it is quite challenging for a single robot to map the whole environment. So, we employ a swarm of robots to perform the mapping. One challenge with this approach is merging sub-maps built by each robot. In this work, we use wireless access points, which are ubiquitous in most urban spaces, to provide us with coarse orientation between sub-maps, and use a custom ICP algorithm to refine this orientation to merge them.

Speedup Simulation for RL using Memoization \& Pre-Caching In-Progress

• Speedup simulation time by 2.5 times for reinforcement learning algorithms
• Parallelize the perception stack by estimating future states and actions and pre-caching them

DARPA OFFSET: Intelligent task planning and execution for UAV and UGV swarms

• Design and implement an interface for the learning agent to interact and operate swarms on multiple target platforms
• Design and implement muti-threaded interaction behaviors between teams of robots
• Debug and test the interface on multiple simulators and real hardware

University at Buffalo, Buffalo, New York, USA

Ph.D. Student, Computer Science (expected graduation date: Dec 2021)

Advisor: Dr. Karthik Dantu

M.S., Computer Science, May 2018

Annamalai University, Chidambaram, Tamilnadu, India

B.E., Computer Science, May, 2009

University at Buffalo, Buffalo, New York, USA

Graduate Student August, 2015 - present

Includes current Ph.D.~research, Ph.D.~and Masters level coursework and research projects.

Research Assistant January, 2018 - present

Duties at various times have included research into high fidelity motion capture and maintaining the SMART Motion Capture Lab, training users on the mocap system and robots like the Baxter, URX arms and the Husky and consulting in design of experiment for motion capture.

Teaching Assistant August, 2017 - December, 2017

Duties at various times have included conducting office hours and recitations for CSE 468/568 Intro to Robotics Algorithms and CSE 487/587 Data Intensive computing. Topics include: kinematics, probabilistic algorithms for localization and mapping, planning, and navigation for Robotics Algorithms and MapReduce and predictive analytics, statistical software packages in R and Python and big data infrastructures like Hadoop and Spark ecosystems for Data Intensive Computing

HCL Technologies, Chennai, Tamilnadu India

Senior Software Engineer Jan, 2010 - Feb, 2014

Engineered several projects, including end-to-end development and maintainance of shopping application with database design, web services, front-ends for the web, phone and television

• Best Project award for final year project in B.E. from Annamalai University
• University award for academics and extra-curricular activities from Annamalai University
• Certificate of Excellence for work from HCL Technologies

• Frameworks: ROS, Tensorflow, PyTorch
• Python, C, C++, C\#, Java, JavaScript
• Algorithms: Simultaneous Localization and Mapping packages, Task Allocation, Multi-agent Task Planning and Reinforcement Learning
• Operating Systems: GNU/Linux, Windows and MacOS