公开(公告)号：US20240362924A1

公开(公告)日：2024-10-31

申请号：US18645882

申请日：2024-04-25

Applicant: Tata Consultancy Services Limited

Inventor： Gireesh NANDIRAJU ,  Ayush AGRAWAL ,  Ahana DATTA ,  Snehasis BANERJEE ,  Mohan SRIDHARAN ,  Madhava KRISHNA ,  Brojeshwar BHOWMICK

IPC: G06V20/58 ,  G05D1/246 ,  G05D1/633 ,  G05D1/644 ,  G05D101/00 ,  G05D101/15 ,  G06T7/246 ,  G06V10/82

CPC classification number: G06V20/58 ,  G05D1/246 ,  G05D1/633 ,  G05D1/644 ,  G06T7/246 ,  G06V10/82 ,  G05D2101/15 ,  G05D2101/22 ,  G06T2207/20084 ,  G06T2207/30261

Abstract: This disclosure relates generally to method and system for multi-object tracking and navigation without pre-sequencing. Multi-object navigation is an embodied Al task where object navigation only searches for an instance of at least one target object where a robot localizes an instance to locate target objects associated with an environment. The method of the present disclosure employs a deep reinforcement learning (DRL) based framework for sequence agnostic multi-object navigation. The robot receives from an actor critic network a deterministic local policy to compute a low-level navigational action to navigate along a shortest path calculated from a current location of the robot to the long-term goal to reach the target object. Here, a deep reinforcement learning network is trained to assign the robot with a computed reward function when the navigational action is performed by the robot to reach an instance of the plurality of target objects.