公开(公告)号：US12043286B2

公开(公告)日：2024-07-23

申请号：US17502769

申请日：2021-10-15

Applicant: Electronics and Telecommunications Research Institute

Inventor： Seonghun Seo ,  Eun Hye Kim

IPC: G01C22/00 ,  B60W60/00 ,  G01P15/18 ,  G01S17/89 ,  G01S17/931 ,  G06F18/213 ,  G06F18/25 ,  G06V20/58 ,  G08G1/16

CPC classification number: B60W60/0016 ,  G01P15/18 ,  G01S17/89 ,  G01S17/931 ,  G06F18/213 ,  G06F18/251 ,  G06V20/58 ,  G08G1/16 ,  B60W2420/408

Abstract: A method and system for detecting a collision by an autonomous robot based on a multi-sensor long short-term memory (LSTM) are disclosed. The method includes generating an input of an LSTM model by combining an input image received from an autonomous robot, light detection and ranging (LiDAR) distance information, and acceleration information, learning a collision alert situation by inputting the input to the LSTM model, and determining a collision situation using an output of the LSTM model and a fully connected neural network (FNN) model.