Zobrazeno 1 - 10
of 10
pro vyhledávání: '"Raviteja Upadrashta"'
Autor:
Partha Pratim Talukdar, Bharadwaj Amrutur, Raviteja Upadrashta, Sagar Gubbi Venkatesh, Anirban Biswas, Vikram Srinivasan
Publikováno v:
ICRA
Robots that can manipulate objects in unstructured environments and collaborate with humans can benefit immensely by understanding natural language. We propose a pipelined architecture of two stages to perform spatial reasoning on the text input. All
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::fccf10bba8d615f63ce6628bf5a774dc
https://doi.org/10.1109/icra48506.2021.9560895
https://doi.org/10.1109/icra48506.2021.9560895
It is highly desirable for robots that work alongside humans to be able to understand instructions in natural language. Existing language conditioned imitation learning models directly predict the actuator commands from the image observation and the
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::3c14b5ff2a61d867c50f83b269e4b6c5
http://arxiv.org/abs/2012.13695
http://arxiv.org/abs/2012.13695
Publikováno v:
IROS
Existing architectures for imitation learning using image-to-action policy networks perform poorly when presented with an input image containing multiple instances of the object of interest, especially when the number of expert demonstrations availab
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::b28f734453114e398c6db113d6090469
https://doi.org/10.1109/iros45743.2020.9341185
https://doi.org/10.1109/iros45743.2020.9341185
Publikováno v:
2020 29th IEEE International Conference on Robot and Human Interactive Communication (RO-MAN).
Robots that must operate in novel environments and collaborate with humans must be capable of acquiring new knowledge from human experts during operation. We propose teaching a robot novel objects it has not encountered before by pointing a hand at t
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::22453e55ba1d6522b75bf62054184989
https://doi.org/10.1109/ro-man47096.2020.9223596
https://doi.org/10.1109/ro-man47096.2020.9223596
Autor:
H.V. Ranjitha, Tarun Choubisa, Raviteja Upadrashta, Joy Kuri, Anurag Kumar, Malati Hegde, A. Praneeth, Madhuri Sheethala Iyer, S. V. R. Anand, Ashwath Narayan Singh, T. V. Prabhakar, P. Vijay Kumar, Sumankumar D. Panchal, Abhijit Bhattacharya, Kaushik Senthoor, Abhirami Sampath
Publikováno v:
LCN Workshops
The aim of the current paper is to describe the challenges faced during the development and deployment of a PIR sensor-based intrusion classification system in an outdoor environment. Some potential solutions to overcome these challenges are also pre
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_________::2239747d00363a3631b08ff5f609f1b4
https://doi.org/10.1109/lcn.2016.041
https://doi.org/10.1109/lcn.2016.041
Autor:
Raviteja Upadrashta, Siddhant Raman, A. Praneeth, V. S. Aswath, Sripad S. Kowshik, T. V. Prabhakar, Madhuri Sheethala Iyer, P. Vijay Kumar, Ajit Prabhu, Tarun Choubisa, Tony Gracious
Publikováno v:
IndraStra Global.
The development of a Passive Infra-Red (PIR) sensing based intrusion detection system is presented here having the ability to reject vegetative clutter and distinguish between human and animal intrusions. This has potential application to reducing hu
Externí odkaz:
https://explore.openaire.eu/search/publication?articleId=doi_dedup___::cd6c7dc5c0c6647adb5f34935cbb1c07
https://igi.indrastra.com/items/show/186576
https://igi.indrastra.com/items/show/186576
Publikováno v:
Synthesis Lectures on Artificial Intelligence & Machine Learning; 2024, pvii-108, 114p
Autor:
Upadrashta, Raviteja, Choubisa, Tarun, Aswath, V. S., Praneeth, A., Prabhu, Ajit, Raman, Siddhant, Gracious, Tony, Vijay Kumar, P., Kowshik, Sripad, Iyer, Madhuri S., Prabhakar, T. V.
Publikováno v:
2015 IEEE Tenth International Conference on Intelligent Sensors, Sensor Networks & Information Processing (ISSNIP); 2015, p1-6, 6p
Publikováno v:
2016 IEEE 41st Conference on Local Computer Networks (LCN); 2016, pxxix-xxix, 1p
This book surveys the state of the art in explainable and interpretable reinforcement learning (RL) as relevant for robotics. While RL in general has grown in popularity and been applied to increasingly complex problems, several challenges have imped