S
Siddarth Venkatraman
Researcher at Manipal Institute of Technology
Publications - 6
Citations - 31
Siddarth Venkatraman is an academic researcher from Manipal Institute of Technology. The author has contributed to research in topics: Deep learning & Steganography. The author has an hindex of 2, co-authored 4 publications receiving 9 citations.
Papers
More filters
Proceedings ArticleDOI
Machine Learning Based Path Planning for Improved Rover Navigation
Neil Abcouwer,Shreyansh Daftry,Tyler del Sesto,Olivier Toupet,Masahiro Ono,Siddarth Venkatraman,Ravi Lanka,Jialin Song,Yisong Yue +8 more
TL;DR: In this paper, the authors present two heuristics that, given a terrain heightmap around the rover, produce cost estimates that more effectively rank the candidate paths before ACE evaluation.
Journal ArticleDOI
MLNav: Learning to Safely Navigate on Martian Terrains
Shreyansh Daftry,Neil Abcouwer,Tyler del Sesto,Siddarth Venkatraman,Jialin Song,Lucas Igel,Amos Byon,Ugo Rosolia,Yisong Yue,Masahiro Ono +9 more
TL;DR: Compared to the baseline ENav path planner on board the Perserverance rover, MLNav can provide a significant improvement in multiple key metrics, such as a 10x reduction in collision checks when navigating real Martian terrains, despite being trained with synthetic terrains.
Posted Content
Machine Learning Based Path Planning for Improved Rover Navigation (Pre-Print Version).
Neil Abcouwer,Shreyansh Daftry,Siddarth Venkatraman,Tyler del Sesto,Olivier Toupet,Ravi Lanka,Jialin Song,Yisong Yue,Masahiro Ono +8 more
TL;DR: This paper presents two heuristics that, given a terrain heightmap around the rover, produce cost estimates that more effectively rank the candidate paths before ACE evaluation, and uses a machine learning (ML) model to predict areas that will be deemed untraversable by ACE.
Posted Content
Deep Residual Neural Networks for Image in Speech Steganography.
TL;DR: A deep learning based technique is proposed to hide a source RGB image message inside finite length speech segments without perceptual loss and to achieve this, three neural networks are trained.
Proceedings ArticleDOI
Deep Residual Neural Networks for Image in Audio Steganography (Workshop Paper)
TL;DR: A deep learning based technique is proposed to hide a source RGB image message inside finite length speech segments without perceptual loss and to achieve this, three neural networks are trained.