Object Goal Navigation using Data Regularized Q-Learning
Object Goal Navigation requires a robot to find and navigate to an instance of a target object class in a previously unseen environment. Our framework incrementally builds a semantic map of the environment over time, and then repeatedly selects a long-term goal ('where to go') based on the semantic map to locate the target object instance. Long-term goal selection is formulated as a vision-based deep reinforcement learning problem. Specifically, an Encoder Network is trained to extract high-level features from a semantic map and select a long-term goal. In addition, we incorporate data augmentation and Q-function regularization to make the long-term goal selection more effective. We report experimental results using the photo-realistic Gibson benchmark dataset in the AI Habitat 3D simulation environment to demonstrate substantial performance improvement on standard measures in comparison with a state of the art data-driven baseline.
Code (0)
등록된 구현이 없습니다.
Tasks
Data AugmentationDeep Reinforcement LearningNavigateObjectQ-LearningSimilar Papers 제목 키워드 기반
Prioritized Semantic Learning for Zero-shot Instance Navigation
We study zero-shot instance navigation, in which the agent navigates to a specific object without using object annotations for training. Previous object navigation approaches apply the image-goal navigation (ImageNav) ta…
Language ModellingObjectPONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learning
State-of-the-art approaches to ObjectGoal navigation rely on reinforcement learning and typically require significant computational resources and time for learning. We propose Potential functions for ObjectGoal Navigatio…
NavigateObjectGoal NavigationObject Goal Navigation using Goal-Oriented Semantic Exploration
This work studies the problem of object goal navigation which involves navigating to an instance of the given object category in unseen environments. End-to-end learning-based navigation methods struggle at this task as …
ObjectRobot NavigationSGoLAM: Simultaneous Goal Localization and Mapping for Multi-Object Goal Navigation
We present SGoLAM, short for simultaneous goal localization and mapping, which is a simple and efficient algorithm for Multi-Object Goal navigation. Given an agent equipped with an RGB-D camera and a GPS/Compass sensor, …
NavigateVisual NavigationPhysics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
Offline Goal-Conditioned Reinforcement Learning (GCRL) holds great promise for domains such as autonomous navigation and locomotion, where collecting interactive data is costly and unsafe. However, it remains challenging…
Reinforcement Learning