Towards Embodied Scene Description
This addresses the limitation of separated semantic understanding in scene description tasks for intelligent agents like robots, though it appears incremental by applying existing learning paradigms to a new task.
The paper tackles the problem of passive scene description by proposing Embodied Scene Description, which enables an agent to find optimal viewpoints for describing scenes, and demonstrates effectiveness on the AI2Thor dataset and a real robotic platform.
Embodiment is an important characteristic for all intelligent agents (creatures and robots), while existing scene description tasks mainly focus on analyzing images passively and the semantic understanding of the scenario is separated from the interaction between the agent and the environment. In this work, we propose the Embodied Scene Description, which exploits the embodiment ability of the agent to find an optimal viewpoint in its environment for scene description tasks. A learning framework with the paradigms of imitation learning and reinforcement learning is established to teach the intelligent agent to generate corresponding sensorimotor activities. The proposed framework is tested on both the AI2Thor dataset and a real world robotic platform demonstrating the effectiveness and extendability of the developed method.