SBIR Phase II: Automated Perception for Robotic Chopsticks Manipulating Small and Large Objects in Constrained Spaces

这一小型企业创新研究(SBIR)第二阶段项目的更广泛/商业影响支持开发机器人解决方案，用于在物流和类似行业中卸载不同形状和大小的非托盘包裹。这项技术可能会为工人提供更熟练的工作，从而消除在不健康的环境中进行体力劳动的需要。该项目寻求通过帮助解决长期存在且日益恶化的员工招聘和留住问题，提高美国在供应链物流领域的竞争力(美国市场规模为1500亿美元/年)。该项目帮助美国成为在受限、非结构化环境中对各种对象进行机器人操作的早期领导者，同时培训能够在安全环境中进行远程操作的劳动力。这个小型企业创新研究(SBIR)第二阶段项目支持开发机器人解决方案，用于在物流和类似行业中卸载不同形状和大小的非托盘包裹。目前，几乎没有商业上可用的自动化解决方案来完成这项任务。这些机器很脆弱，速度很慢，只有在统一的包装下才能很好地工作。研究目标包括：1)升级机器人的感知系统，将高速视觉和力感觉输入融合在一起，从而实现更快、更健壮、更安全、更少的包装损坏；2)升级机器人的视觉系统，以感知盒子以外的物体类别；3)研究用户界面，使操作员能够最容易地纠正不可避免的感知系统错误；以及4)现场测试机器人系统。累积的结果将是一个经过严格验证的系统，它可以安全地(对于包和用户)高速运行，几乎不需要人工干预。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader/commercial impact of this Small Business Innovation Research (SBIR) Phase II project supports the development of robotic solutions for unloading non-palletized packages of different shapes and sizes in logistics and similar industries. This technology may provide workers with more skilled jobs that remove the need for physically strenuous labor in unhealthy environments. The project seeks to increase US competitiveness in supply chain logistics ($150 billion / year market in the US) by helping solve long-standing and worsening employee recruitment and retention problems. The project helps the US become an early leader in the robotic manipulation of diverse objects in constrained, unstructured environments while simultaneously training a workforce capable of remote manipulation in safe environments.This Small Business Innovation Research (SBIR) Phase II project supports the development of robotic solutions for unloading non-palletized packages of different shapes and sizes in logistics and similar industries. At present, there are few commercially-available automated solutions for this task. Those few machines are brittle, slow, and only work well with uniform packages. The research objectives include: 1) upgrading the robot’s perception system to fuse high-speed vision and force sensory inputs, which will enable closed-loop picking with greater speed, more robustness, higher safety, and less package damage; 2) upgrading the robot’s vision system to perceive object categories beyond boxes; 3) investigating a user interface to allow a human operator to most-easily correct inevitable perception system errors; and 4) field testing the robotic system. The cumulative result will be a rigorously validated system that safely (for packages and users) operates at high speed with little manual intervention.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.