The generalization of the end-to-end deep reinforcement learning (DRL) for
object-goal visual navigation is a long-standing challenge since object classes
and placements vary in new test environments. Learning domain-independent
visual representation is critical for enabling the trained DRL agent with the
ability to generalize to unseen scenes and objects. In this letter, a
target-directed attention network (TDANet) is proposed to learn the end-to-end
object-goal visual navigation policy with zero-shot ability. TDANet features a
novel target attention (TA) module that learns both the spatial and semantic
relationships among objects to help TDANet focus on the most relevant observed
objects to the target. With the Siamese architecture (SA) design, TDANet
distinguishes the difference between the current and target states and
generates the domain-independent visual representation. To evaluate the
navigation performance of TDANet, extensive experiments are conducted in the
AI2-THOR embodied AI environment. The simulation results demonstrate a strong
generalization ability of TDANet to unseen scenes and target objects, with
higher navigation success rate (SR) and success weighted by length (SPL) than
other state-of-the-art models.

提出了一种目标导向的注意网络（TDANet），用于学习具有零 - shot 能力的端到端目标导向视觉导航策略，并通过在 AI2-THOR 环境中进行的大量实验验证了 TDANet 的导航性能，其在未见过的场景和目标对象上表现出较高的导航成功率和成功率加权长度，优于其他最先进的模型。