Zobrazeno 1 - 10
of 236
pro vyhledávání: '"Krishna, K Madhava"'
Autor:
Pathre, Pranjali, Gupta, Gunjan, Qureshi, M. Nomaan, Brunda, Mandyam, Brahmbhatt, Samarth, Krishna, K. Madhava
Visual servoing, the method of controlling robot motion through feedback from visual sensors, has seen significant advancements with the integration of optical flow-based methods. However, its application remains limited by inherent challenges, such
Externí odkaz:
http://arxiv.org/abs/2410.12432
Autor:
Kumar, Naman, Singha, Antareep, Nanwani, Laksh, Potdar, Dhruv, R, Tarun, Rastgar, Fatemeh, Idoko, Simon, Singh, Arun Kumar, Krishna, K. Madhava
Navigation amongst densely packed crowds remains a challenge for mobile robots. The complexity increases further if the environment layout changes, making the prior computed global plan infeasible. In this paper, we show that it is possible to dramat
Externí odkaz:
http://arxiv.org/abs/2409.16011
Autor:
Chavan, Aneesh, Agrawal, Vaibhav, Bhat, Vineeth, Chittawar, Sarthak, Srivastava, Siddharth, Arora, Chetan, Krishna, K Madhava
Re-identification (ReID) is a critical challenge in computer vision, predominantly studied in the context of pedestrians and vehicles. However, robust object-instance ReID, which has significant implications for tasks such as autonomous exploration,
Externí odkaz:
http://arxiv.org/abs/2409.12002
Autor:
Nanwani, Laksh, Gupta, Kumaraditya, Mathur, Aditya, Agrawal, Swayam, Hafez, A. H. Abdul, Krishna, K. Madhava
Publikováno v:
Advanced Robotics - Taylor and Francis - 2024
Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work SI Maps [1] showed that having instance-level information and the semantic understa
Externí odkaz:
http://arxiv.org/abs/2404.17922
Autor:
Singh, Gaurav, Kalwar, Sanket, Karim, Md Faizal, Sen, Bipasha, Govindan, Nagamanikandan, Sridhar, Srinath, Krishna, K Madhava
Efficiently generating grasp poses tailored to specific regions of an object is vital for various robotic manipulation tasks, especially in a dual-arm setup. This scenario presents a significant challenge due to the complex geometries involved, requi
Externí odkaz:
http://arxiv.org/abs/2404.04643
Autor:
Manoharan, Amith, Sharma, Aditya, Belsare, Himani, Pal, Kaustab, Krishna, K. Madhava, Singh, Arun Kumar
Navigation of wheeled vehicles on uneven terrain necessitates going beyond the 2D approaches for trajectory planning. Specifically, it is essential to incorporate the full 6dof variation of vehicle pose and its associated stability cost in the planni
Externí odkaz:
http://arxiv.org/abs/2404.03307
Existing Vision-Language models (VLMs) estimate either long-term trajectory waypoints or a set of control actions as a reactive solution for closed-loop planning based on their rich scene comprehension. However, these estimations are coarse and are s
Externí odkaz:
http://arxiv.org/abs/2403.20116
Point cloud prediction is an important yet challenging task in the field of autonomous driving. The goal is to predict future point cloud sequences that maintain object structures while accurately representing their temporal motion. These predicted p
Externí odkaz:
http://arxiv.org/abs/2401.17399
Autor:
Patel, Dhruv, Chepuri, Shivani, Thakur, Sarvesh, Harikumar, K., S., Ravi Kiran, Krishna, K. Madhava
Despite the technological advancements in the construction and surveying sector, the inspection of salient features like windows in an under-construction or existing building is predominantly a manual process. Moreover, the number of windows present
Externí odkaz:
http://arxiv.org/abs/2311.14635
In this paper we show an effective means of integrating data driven frameworks to sampling based optimal control to vastly reduce the compute time for easy adoption and adaptation to real time applications such as on-road autonomous driving in the pr
Externí odkaz:
http://arxiv.org/abs/2310.13077