[2M6-GS-10] AI application

[2M6-GS-10-03] Target Region Prediction from Navigation Instructions in Urban Areas

〇Shumpei Hatanaka¹, Wei Yang¹, Katsuyuki Kuyo¹, Naoki Hosomi², Teruhisa Misu³, Kentaro Yamada², Komei Sugiura¹ (1. Keio University, 2. Honda R&D Co., Ltd. , 3. Honda Research Institute USA, Inc.)

Keywords:Understanding Navigation Instructions Task, Target Regions Prediction, Trimodal, Semantic Segmentation Mask, Autonomous Driving

In this work, we propose a Trimodal Navigable Region Segmentation Model (TNRSM), which can handle three modalities: image, navigation instruction, and semantic segmentation masks. We validated our model on the Talk2Car-Regseg dataset. The results demonstrated that our method outperformed the baseline method in all evaluation metrics in the Referring Navigable Regions task.