Krishna Jaganathan
B.S. Computer Engineering
Georgia Institute of Technology
kjaganathan7 at gatech dot edu
B.S. Computer Engineering
Georgia Institute of Technology
kjaganathan7 at gatech dot edu
I'm Krishna, an undergraduate in computer engineering at Georgia Tech. I am a researcher at the RIPL Lab (Prof. Zsolt Kira) and IVALab (Prof. Patricio Vela). I'm interested in multimodal large language models for grounding robot perception and navigation, along with 3D reconstruction for robot policy training to reduce the sim-to-real gap in embodied AI. Most recently, I've been exploring modality hallucination to improve semantic segmentation for downstream object goal navigation tasks without depth information.
B.S. Computer Engineering
GPA: 4.0 / 4.0
Research Advisors
IEEE International Symposium on a World of Wireless, Mobile and Multimedia Networks (WoWMoM) Under Review
NeurIPS 2024 High School Track - Spotlight
A project employing vision-language models (VLMs) for efficient robot perception and dynamic path planning. The system synthesizes probabilistic Hough transforms with semantic scene information to optimize edge detection and obstacle identification, intelligently partitions environments to decide optimal paths, and performs VLM-guided terrain analysis for adaptive motor control on varied surfaces.
A navigation and control system for autonomous vehicles combining the Pure Pursuit controller with a novel O(1) motion profiling algorithm. Features real-time feedback from IMU and wheel velocities, path replanning based on probability metrics, arc-length parameterized Bezier curve path generation, and automated PID tuning via regression on previously executed paths.
