US 12,449,821 B2
Autonomous source localization
Khurram Hassan-Shafique, Ashburn, VA (US); Zeeshan Rasheed, Ashburn, VA (US); Alireza Zaeemzadeh, Ashburn, VA (US); Emmanuel Tung, Ashburn, VA (US); and Eric Chen, Ashburn, VA (US)
Assigned to Novateur Research Solutions, Ashburn, VA (US)
Filed by Novateur Research Solutions, Ashburn, VA (US)
Filed on Apr. 2, 2024, as Appl. No. 18/624,947.
Prior Publication US 2025/0306594 A1, Oct. 2, 2025
Int. Cl. G05D 1/60 (2024.01); G05D 1/223 (2024.01); G05D 1/229 (2024.01); G05D 1/248 (2024.01); G05D 101/15 (2024.01); G05D 105/80 (2024.01); G05D 111/10 (2024.01); G05D 111/20 (2024.01); G05D 111/30 (2024.01); G05D 111/50 (2024.01); G05D 111/67 (2024.01)
CPC G05D 1/60 (2024.01) [G05D 1/223 (2024.01); G05D 1/229 (2024.01); G05D 1/248 (2024.01); G05D 2101/15 (2024.01); G05D 2105/80 (2024.01); G05D 2111/17 (2024.01); G05D 2111/20 (2024.01); G05D 2111/30 (2024.01); G05D 2111/56 (2024.01); G05D 2111/67 (2024.01)] 21 Claims
OG exemplary drawing
 
1. An autonomous source localization system comprising:
a robotic platform comprising a plurality of sensors that collect visual, non-visual, and gas concentration data of an environment being sensed by the plurality of sensors;
a module that integrates the visual, non-visual, and gas concentration data into a joint embedding space using a neural network architecture, wherein the neural network architecture is based on a transformer architecture;
a processor to:
receive the joint embedding space from the module;
receive a history of system states and actions of the robotic platform wherein the history of system states and actions comprises a location and orientation of the robotic platform and previous actions taken by the robotic platform; and
select an operational action for the robotic platform based on the joint embedding space, the history of system states and actions, and neural network inputs into the processor;
a robotic interface that causes the robotic platform to perform the operational action selected by the processor.