We propose a light-weight, self-supervised adaptation for a visual navigation agent to generalize to unseen environment. Given an embodied agent trained in a noiseless environment, our objective is to transfer the agent to a noisy environment where actuation and odometry sensor noise is present. Our method encourages the agent to maximize the consistency between the global maps generated at different time steps in a round-trip trajectory. The proposed task is completely self-supervised, not requiring any supervision from ground-truth pose data or explicit noise model. In addition, optimization of the task objective is extremely light-weight, as training terminates within a few minutes on a commodity GPU. Our experiments show that the proposed task helps the agent to successfully transfer to new, noisy environments. The transferred agent exhibits improved localization and mapping accuracy, further leading to enhanced performance in downstream visual navigation tasks. Moreover, we demonstrate test-time adaptation with our self-supervised task to show its potential applicability in real-world deployment.
翻译:我们建议对视觉导航剂进行轻量、自我监督的适应,以便向看不见的环境推广。鉴于一个在无噪音环境中受过训练的装饰剂,我们的目标是将该剂转移到一个有振动和异地感应器噪音的吵闹环境中。我们的方法鼓励该剂在圆轨轨道不同时段生成的全球地图之间最大限度地保持一致。拟议的任务是完全自我监督,不要求从地面真相中生成任何数据或明确的噪音模型进行任何监督。此外,任务目标的优化是极轻的,因为培训将在几分钟内结束对商品GPU的培训。我们的实验表明,拟议的任务有助于该剂成功地向新的、吵闹的环境转移。被转移的代理人展示了本地化和绘图准确性,从而进一步提高了下游视觉导航任务的性能。此外,我们展示了我们自我监督的任务的测试时间适应性,以显示其在现实世界部署中的潜在适用性。