Ajitem Joshi
Papers
1
Total Citations
13
H-Index
1
About
Ajitem Joshi is a researcher at the forefront of decentralized artificial intelligence, with a primary focus on federated learning and multi-robot systems. His most-cited work, "On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios" (2022, 13 citations), tackles a critical challenge in distributed AI: moving beyond traditional server-dependent aggregation to enable truly peer-to-peer collaboration among robots. This contribution is particularly significant for privacy-sensitive and bandwidth-constrained environments, where central servers pose bottlenecks and security risks. By proposing a decentralized framework for federated reinforcement learning, Joshi empowers robot swarms to learn collectively without compromising data locality or requiring constant cloud connectivity. His research bridges the gap between theoretical federated learning and practical multi-robot deployment, offering scalable solutions for autonomous navigation, disaster response, and industrial automation. With a growing citation footprint, Joshi’s work is gaining traction among researchers seeking robust, privacy-preserving AI for edge devices. His achievements underscore a commitment to making collaborative machine learning both efficient and resilient—a vital step toward truly autonomous, decentralized intelligence.
Research Focus
Key Achievements
Top Papers
- 1On Decentralizing Federated Reinforcement Learning in Multi-Robot Scenarios13 citations · 2022