Harikumar Kandath
International Institute of Information Technology, Hyderabad
48 Papers
21 Citations
Harikumar Kandath is an academic researcher from International Institute of Information Technology, Hyderabad. The author has contributed to research in topics: Computer science & Control theory. The author has an hindex of 3, co-authored 17 publications. Previous affiliations of Harikumar Kandath include Nanyang Technological University & International Institute of Information Technology.
Chat about Author
Papers
Twin actor twin delayed deep deterministic policy gradient (TATD3) learning for batch process control
TL;DR: In this article, an actor-critic RL algorithm, namely, twin actor twin delayed deep deterministic policy gradient (TATD3), was proposed by incorporating twin actor networks in the existing twin-delayed DDPG algorithm for the continuous control.
33
Autonomous Navigation and Sensorless Obstacle Avoidance for UGV with Environment Information from UAV
Harikumar Kandath,Titas Bera,Rajarshi Bardhan,Suresh Sundaram +3 more
- 01 Jan 2018
TL;DR: The problem of obstacle avoidance for an unmanned ground vehicle (UGV) under the event of sensor failure is addressed and the proposed obstacle avoidance method is experimentally validated in the outdoor environment with an autonomous UAV equipped with a camera and anonomous UGV navigating based on GPS localization and environment information from the UAV.
33
Dynamic Area Coverage for Multi-UAV Using Distributed UGVs: A Two-Stage Density Estimation Approach
Senthilnath Jayavelu,Harikumar Kandath,Suresh Sundaram +2 more
- 01 Jan 2018
TL;DR: This paper focuses on increasing the duration of autonomous missions performed by UAVs by deploying a swarm of Unmanned Ground Vehicles (UGVs) as mobile refueling and maintenance stations by proposing a two-stage density estimation approach.
9
A decentralized learning strategy to restore connectivity during multi-agent formation control
TL;DR: In this paper , a decentralized learning algorithm is proposed to restore communication connectivity in multi-agent formation control, where each mobile agent in the proposed scheme learns to raise the team connectivity when the inter-agent communication is lost.
8
•Posted Content
Application of twin delayed deep deterministic policy gradient learning for the control of transesterification process.
Tanuja Joshi,Shikhar Makker,Hariprasad Kodamana,Harikumar Kandath +3 more
- 25 Feb 2021
TL;DR: In this paper, the authors exploit the application of twin delayed deep deterministic policy gradient (TD3) based RL for continuous control of the batch transesterification process and demonstrate that TD3 based controller is able to control the process and can be a promising direction towards the goal of artificial intelligence-based control in process industries.
7