TY - GEN
T1 - Spatial Relation Graph and Graph Convolutional Network for Object Goal Navigation
AU - Sasi Kiran, D. A.
AU - Anand, Kritika
AU - Kharyal, Chaitanya
AU - Kumar, Gulshan
AU - Gireesh, Nandiraju
AU - Banerjee, Snehasis
AU - Roychoudhury, Ruddra Dev
AU - Sridharan, Mohan
AU - Bhowmick, Brojeshwar
AU - Krishna, Madhava
N1 - Publisher Copyright:
© 2022 IEEE.
PY - 2022/10/28
Y1 - 2022/10/28
N2 - This paper describes a framework for the object-goal navigation (ObjectNav) task, which requires a robot to find and move to an instance of a target object class from a random starting position. The framework uses a history of robot trajectories to learn a Spatial Relational Graph (SRG) and Graph Convolutional Network (GCN)-based embeddings for the likelihood of proximity of different semantically-labeled regions and the occurrence of different object classes in these regions. To locate a target object instance during evaluation, the robot uses Bayesian inference and the SRG to estimate the visible regions, and uses the learned GCN embeddings to rank visible regions and select the region to explore next. This approach is tested using the Matterport3D (MP3D) benchmark dataset of indoor scenes in AI Habitat, a visually realistic simulation environment, to report substantial performance improvement in comparison with state of the art baselines.
AB - This paper describes a framework for the object-goal navigation (ObjectNav) task, which requires a robot to find and move to an instance of a target object class from a random starting position. The framework uses a history of robot trajectories to learn a Spatial Relational Graph (SRG) and Graph Convolutional Network (GCN)-based embeddings for the likelihood of proximity of different semantically-labeled regions and the occurrence of different object classes in these regions. To locate a target object instance during evaluation, the robot uses Bayesian inference and the SRG to estimate the visible regions, and uses the learned GCN embeddings to rank visible regions and select the region to explore next. This approach is tested using the Matterport3D (MP3D) benchmark dataset of indoor scenes in AI Habitat, a visually realistic simulation environment, to report substantial performance improvement in comparison with state of the art baselines.
KW - Cognitive Robotics
KW - Graph Convolutional Networks (GCN)
KW - Node Embeddings
KW - Semantic Object Navigation
U2 - 10.1109/CASE49997.2022.9926534
DO - 10.1109/CASE49997.2022.9926534
M3 - Conference contribution
AN - SCOPUS:85141701098
T3 - IEEE International Conference on Automation Science and Engineering
SP - 1392
EP - 1398
BT - 2022 IEEE 18th International Conference on Automation Science and Engineering, CASE 2022
PB - IEEE Computer Society Press
T2 - 18th IEEE International Conference on Automation Science and Engineering, CASE 2022
Y2 - 20 August 2022 through 24 August 2022
ER -