乐飞大香蕉电影网品味
垃圾分拣机器人:为垃圾分类回收而生
日期:2019-06-14 19:29    编辑:乐飞大香蕉电影网    来源:未知
麻省理工学院的 RoCycle 系统用一只柔软的、防穿刺的手来分拣回收垃圾。指尖上的压力传感器可以探测到物体的大小和材质。然后它自动将物品放入相应的回收垃 [ti:小e大香蕉电影] [ar:小e大香蕉电影这个机器人能自动分类可回收的垃圾。 [00:03.28]The RoCycle system by M.

  麻省理工学院的 “RoCycle” 系统用一只柔软的、防穿刺的手来分拣回收垃圾。指尖上的压力传感器可以探测到物体的大小和材质。然后它自动将物品放入相应的回收垃 [ti:小e大香蕉电影] [ar:小e大香蕉电影这个机器人能自动分类可回收的垃圾。 [00:03.28]The RoCycle system by M.I.T. has a soft, puncture-resistant hand. 麻省理工学院的 “RoCycle” 系统用一只柔软的、防穿刺的手来分拣回收垃圾。 [00:10.45]Pressure sensors on its fingertips detect an objects size and material. 指尖上的压力传感器可以探测到物体的大小和材质。 [00:14.84]It then autonomously places the item in the appropriate recycle bin. 然后它自动将物品放入相应的回收垃圾箱。 [00:18.83]With computer vision alone, the systems are not able to separate paper from plastic. “单凭计算机视觉,这些系统无法将纸张与塑料分开。 [00:25.99]Many paper and plastic cups look the same, but by introducing the ability to squeeze the objects and to know whether its flexible or not - we are able to go one step beyond what todays methods can do. 许多纸杯和塑料杯看起来是一样的,但是通过引入挤压物体的能力,并辨别它是否有弹性、可弯曲,我们则能够超越现有的方法。” [00:40.20]The goal of the system is to reduce the back-end cost of recycling. 该系统的目标是降低后端回收成本。 [00:44.93]It currently has 85 percent accuracy in identifying stationary items, but only 63 percent accuracy on a simulated conveyer belt. 目前,它识别静止物体的准确率为 85%,但在模拟输送带上的准确率仅为 63%。 [00:54.63]A common error was identifying paper-covered tins as paper. 一个常见的错误是把外包装由纸覆盖的金属罐头盒识别成纸。 [00:58.65]But how are researchers looking to improve the system? 那么研究人员在如何改进这个系统? [01:01.75]We plan to create a much more detailed sensorised skin. “我们计划创造一个更精细的传感皮肤。 [01:06.92]We plan to develop the hand at different sizes and we plan to improve our algorithms for recognition. 我们还计划研制不同大小的手,并改进我们的识别算法。 [01:14.73]Were very excited to see the use of robot automation in solving a problem that matters globally. 我们很高兴看到机器人自动化在解决一个全球性问题上的应用。”垃圾分拣机器人:为垃圾分类回收而生

  • 本类最新
  • 时尚
  • 新闻
  • 生活
  • 视觉
  • 微爱
返回顶部