Skip to content

Commit 93e3de6

Browse files
karthiks1701claude
andcommitted
feat: add Karthik Soma's profile to the people section
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
1 parent f65aabe commit 93e3de6

1 file changed

Lines changed: 28 additions & 0 deletions

File tree

src/people/karthik-soma.md

Lines changed: 28 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,28 @@
1+
---
2+
name: Karthik Soma
3+
role: phd
4+
title: PhD Student
5+
short_bio: PhD student at Mila and Polytechnique Montréal working on swarm intelligence, collective decision-making, and multi-agent reinforcement learning.
6+
supervisor: Giovanni Beltrame
7+
tags: [Swarm Robotics, Multi-Agent Reinforcement Learning, Collective Intelligence]
8+
email: karthik.soma@etud.polymtl.ca
9+
github: karthiks1701
10+
linkedin: https://www.linkedin.com/in/karthik-soma-b92166162/
11+
scholar: eJ5jLXoAAAAJ
12+
---
13+
14+
Karthik Soma is a PhD student at Polytechnique Montréal and Mila Quebec AI Institute, supervised by Prof. Giovanni Beltrame. He holds a B.Tech in Instrument and Control Engineering from the National Institute of Technology, Tiruchirappalli (GPA: 8.98/10.00).
15+
16+
His research spans swarm intelligence, collective decision-making, and multi-agent reinforcement learning. He has published work at top robotics and AI venues including ICRA, TMLR, MRS, DARS, and ECAI.
17+
18+
## Current Work
19+
20+
Karthik's doctoral work focuses on collective intelligence in robot swarms — exploring how large groups of simple robots can make decisions, share resources, and navigate collaboratively. Current projects include:
21+
22+
- **Swarm Biotactics**: Developing collective strategies for centroid estimation, flocking, and navigation using bio-hybrid swarms.
23+
- **Multi-Agent Reinforcement Learning**: Benchmarking MARL algorithms in complex coordination tasks with heterogeneous agents, in collaboration with Thales Digital Solutions Inc.
24+
- **The Hive Mind**: Investigating how swarm behavior emerges from a single RL agent trained across a population of robots.
25+
26+
## Contact
27+
28+
Reach Karthik at [karthik.soma@etud.polymtl.ca](mailto:karthik.soma@etud.polymtl.ca) or on [LinkedIn](https://www.linkedin.com/in/karthik-soma-b92166162/).

0 commit comments

Comments
 (0)