9 Hits in 1.3 sec

Robot-Initiated Specification Repair through Grounded Language Interaction [article]

Adrian Boteanu, Jacob Arkin, Siddharth Patki, Thomas Howard, Hadas Kress-Gazit
2017 arXiv   pre-print
Robots are required to execute increasingly complex instructions in dynamic environments, which can lead to a disconnect between the user's intent and the robot's representation of the instructions. In this paper we present a natural language instruction grounding framework which uses formal synthesis to enable the robot to identify necessary environment assumptions for the task to be successful. These assumptions are then expressed via natural language questions referencing objects in the
more » ... onment. The user is prompted to confirm or reject the assumption. We demonstrate our approach on two tabletop pick-and-place tasks.
arXiv:1710.01417v1 fatcat:5qhiwtc3nreudgfwjau7nxopie

Language-guided Semantic Mapping and Mobile Manipulation in Partially Observable Environments [article]

Siddharth Patki, Ethan Fahnestock, Thomas M. Howard, Matthew R. Walter
2019 arXiv   pre-print
Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment to be known a priori, and they attempt to reason over a world representation that is flat and unnecessarily detailed, which limits scalability. Recent semantic mapping methods address partial observability by exploiting language as a sensor to infer a
more » ... ution over topological, metric and semantic properties of the environment. However, maintaining a distribution over highly detailed maps that can support grounding of diverse instructions is computationally expensive and hinders real-time human-robot collaboration. We propose a novel framework that learns to adapt perception according to the task in order to maintain compact distributions over semantic maps. Experiments with a mobile manipulator demonstrate more efficient instruction following in a priori unknown environments.
arXiv:1910.10034v1 fatcat:xvtsqctqu5aq3jl4gl6kkbpyoi

Language-guided Adaptive Perception with Hierarchical Symbolic Representations for Mobile Manipulators [article]

Ethan Fahnestock, Siddharth Patki, Thomas M. Howard
2019 arXiv   pre-print
Specifics on these symbols can be found in (Patki and Howard 2018) .  ...  If we consider more complicated tasks beyond simple grasping (Patki and Howard 2018) or navigation (Patki et al. 2019), we will encounter scenarios where the fidelity of the world representation needed  ... 
arXiv:1909.09880v1 fatcat:p6ak36k56ra4xmpvpdxpgwmlxi

Inferring Compact Representations for Efficient Natural Language Understanding of Robot Instructions [article]

Siddharth Patki and Andrea F. Daniele and Matthew R. Walter and Thomas M. Howard
2019 arXiv   pre-print
., the "world model") that expresses all metric [6] [7] [8] [9] [10] [11] [12] as well as semantic [4, 5, [13] [14] [15] [16] knowledge Siddharth Patki and Thomas M.  ... 
arXiv:1903.09243v1 fatcat:xxl5ora4zvd3pku7smactjqdxy

Language-Guided Adaptive Perception for Efficient Grounded Communication with Robotic Manipulators in Cluttered Environments

Siddharth Patki, Thomas Howard
2018 Proceedings of the 19th Annual SIGdial Meeting on Discourse and Dialogue  
The utility of collaborative manipulators for shared tasks is highly dependent on the speed and accuracy of communication between the human and the robot. The run-time of recently developed probabilistic inference models for situated symbol grounding of natural language instructions depends on the complexity of the representation of the environment in which they reason. As we move towards more complex bi-directional interactions, tasks, and environments, we need intelligent perception models
more » ... t can selectively infer precise pose, semantics, and affordances of the objects when inferring exhaustively detailed world models is inefficient and prohibits real-time interaction with these robots. In this paper we propose a model of language and perception for the problem of adapting the configuration of the robot perception pipeline for tasks where constructing exhaustively detailed models of the environment is inefficient and inconsequential for symbol grounding. We present experimental results from a synthetic corpus of natural language instructions for robot manipulation in example environments. The results demonstrate that by adapting perception we get significant gains in terms of run-time for perception and situated symbol grounding of the language instructions without a loss in the accuracy of the latter.
doi:10.18653/v1/w18-5016 dblp:conf/sigdial/PatkiH18 fatcat:alzd6o6g2fbfvbm3uxcurkem6i

Language Understanding for Field and Service Robots in a Priori Unknown Environments

Matthew Walter, Siddharth Patki, Andrea Daniele, Ethan Fahnestock, Felix Duvallet, Sachithra Hemachandra, Jean Oh, Anthony Stentz, Nicholas Roy, Thomas Howard
2022 Field Robotics  
., 2017; Patki and Howard, 2018; Arkin et al., 2018; Patki et al., 2019; Arkin et al., 2020) .  ...  Addressing this scalability challenge, a recent line of work (Patki and Howard, 2018; Patki et al., 2019 Patki et al., , 2020) ) proposes learning to adapt the robot's perception pipeline by exploiting  ... 
doi:10.55417/fr.2022040 fatcat:2zcvlzqehfghtlispn3m7dhwy4


V Patki, S Bhargava, R Soloman, V Gupta, M Patel, A Jagadeesh
Serum Thyroid Profile In Critically Ill Children Vinayak Patki , Jennifer S.  ...  Dillon, Vidya Patki Dept Of Pediatrics, Wanless Hospital, Miraj 416410,Dist-Sangli,Maharashtra Hall B 1 . 1 -T T levels were low in critically ill patients.  ... 
doi:10.21304/2014.0101.00011 fatcat:wjot77ufebek3nachgib7grppa

Dark Silicon: From Embedded to HPC Systems (Dagstuhl Seminar 16052)

Hans Michael Gerndt, Michael Glaß, Sri Parameswaran, Barry L. Rountree, Marc Herbstritt
2016 Dagstuhl Reports  
Tapasay Patki presented application workflows as a mean to gather such information.  ...  Static tuning of parameters, such as the power budget of an application, were presented by Michael Knobloch and Tapasya Patki.  ... 
doi:10.4230/dagrep.6.1.224 dblp:journals/dagstuhl-reports/GerndtGPR16 fatcat:fnfmxyiknfehxfnlomovzifrh4

[Front matter]

2022 2022 9th International Conference on Computing for Sustainable Global Development (INDIACom)   unpublished
Learning Models for Sentiment Analysis on Movie Review Data Monir Yahya Ali Salmony and Arman Rasool Faridi 71. 577 A Decentralized Approach for Evidence Management in Archaeology Rishabh Nevatia, Arya Patki  ...  Kumar and Ritu Dewan 65. 532 Stochastic Optimization of Sensor's Deployment Location over Terrain to Maximize Viewshed Coverage Area for a Fixed Number of Sensors Scenario Vivek Saxena, Rohul Shukla and Siddharth  ... 
doi:10.23919/indiacom54597.2022.9763121 fatcat:wlljcwmvebc4xjmcr5okln4jda