arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1809.07207cs.RO
收藏

学习远程感知使用自我监督从短程传感器和里程计

Learning Long-Range Perception Using Self-Supervision from Short-Range Sensors and Odometry

Dalle Molle Institute for Artificial Intelligence (IDSIA), USI-SUPSI(人工智能达莱莫尔研究所(IDSIA),瑞士意大利语区大学-苏佩里诺理工学院(USI-SUPSI))

Mirko Nava, Jerome Guzzi, R. Omar Chavez-Garcia, Luca M. Gambardella, Alessandro Giusti

摘要:

我们引入了一个一般的自我监督的方法来预测未来的输出的短距离传感器(如接近传感器)给定的当前输出的长距离传感器(如摄像头);我们假设,前者是直接相关的一些信息被感知(如障碍物的存在,在一个给定的位置),而后者是信息丰富,但很难直接解释。我们实例化和实现的方法,在一个小型移动机器人检测障碍物在不同的距离使用机器人的前向摄像头的视频流,通过训练自动获取的数据集上的卷积神经网络。我们定量地评估质量的预测看不见的情况下,定性地评估不同的操作条件下的鲁棒性,并演示使用作为唯一的输入的避障控制器。我们还实例化的方法在一个不同的模拟场景与互补的特点,以证明我们的贡献的一般性。

英文摘要:

We introduce a general self-supervised approach to predict the future outputs of a short-range sensor (such as a proximity sensor) given the current outputs of a long-range sensor (such as a camera); we assume that the former is directly related to some piece of information to be perceived (such as the presence of an obstacle in a given position), whereas the latter is information-rich but hard to interpret directly. We instantiate and implement the approach on a small mobile robot to detect obstacles at various distances using the video stream of the robot's forward-pointing camera, by training a convolutional neural network on automatically-acquired datasets. We quantitatively evaluate the quality of the predictions on unseen scenarios, qualitatively evaluate robustness to different operating conditions, and demonstrate usage as the sole input of an obstacle-avoidance controller. We additionally instantiate the approach on a different simulated scenario with complementary characteristics, to exemplify the generality of our contribution.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑