Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation
This addresses the inefficiency of retraining models for each new navigation task, benefiting researchers and practitioners in robotics and AI by reducing computational costs and improving adaptability.
The paper tackles the problem of expensive and task-specific training in visual navigation by introducing a modular transfer learning model that enables zero-shot experience learning across multiple tasks and goal modalities, achieving faster learning, better generalization, and outperforming state-of-the-art models by a significant margin.
In reinforcement learning for visual navigation, it is common to develop a model for each new task, and train that model from scratch with task-specific interactions in 3D environments. However, this process is expensive; massive amounts of interactions are needed for the model to generalize well. Moreover, this process is repeated whenever there is a change in the task type or the goal modality. We present a unified approach to visual navigation using a novel modular transfer learning model. Our model can effectively leverage its experience from one source task and apply it to multiple target tasks (e.g., ObjectNav, RoomNav, ViewNav) with various goal modalities (e.g., image, sketch, audio, label). Furthermore, our model enables zero-shot experience learning, whereby it can solve the target tasks without receiving any task-specific interactive training. Our experiments on multiple photorealistic datasets and challenging tasks show that our approach learns faster, generalizes better, and outperforms SoTA models by a significant margin.