Practical global path planning is critical for commercializing cleaning robots working in semi-structured environments. In the literature, global path planning methods for free space usually focus on path length and neglect the traffic rule constraints of the environments, which leads to high-frequency re-planning and increases collision risks. In contrast, those for structured environments are developed mainly by strictly complying with the road network representing the traffic rule constraints, which may result in an overlong path that hinders the overall navigation efficiency. This article proposes a general and systematic approach to improve global path planning performance in semi-structured environments. A unidirectional road network is built to represent the traffic constraints in semi-structured environments and a hybrid strategy is proposed to achieve a guaranteed planning result.Cutting across the road at the starting and the goal points are allowed to achieve a shorter path. Especially, a two-layer potential map is proposed to achieve a guaranteed performance when the starting and the goal points are in complex intersections. Comparative experiments are carried out to validate the effectiveness of the proposed method. Quantitative experimental results show that, compared with the state-of-art, the proposed method guarantees a much better balance between path length and the consistency with the road network.

Assembling a slave object into a fixture-free master object represents a critical challenge in flexible manufacturing. Existing deep reinforcement learning-based methods, while benefiting from visual or operational priors, often struggle with small-batch precise assembly tasks due to their reliance on insufficient priors and high-costed model development. To address these limitations, this paper introduces a cognitive manipulation and learning approach that utilizes skill graphs to integrate learning-based object detection with fine manipulation models into a cohesive modular policy. This approach enables the detection of the master object from both global and local perspectives to accommodate positional uncertainties and variable backgrounds, and parametric residual policy to handle pose error and intricate contact dynamics effectively. Leveraging the skill graph, our method supports knowledge-informed learning of semi-supervised learning for object detection and classroom-to-real reinforcement learning for fine manipulation. Simulation experiments on a gear-assembly task have demonstrated that the skill-graph-enabled coarse-operation planning and visual attention are essential for efficient learning and robust manipulation, showing substantial improvements of 13$\%$ in success rate and 15.4$\%$ in number of completion steps over competing methods. Real-world experiments further validate that our system is highly effective for robotic assembly in semi-structured environments.

One kind of robot has endured for the last half-century: the hulking one-armed Goliaths that dominate industrial assembly lines. These industrial robots have been task-specific -- built to spot weld, say, or add threads to the end of a pipe. They aren't sexy, but in the latter half of the 20th century they transformed industrial manufacturing and, with it, the low- and medium-skilled labor landscape in much of the US, Asia, and Europe. You've probably been hearing a lot more about robots and robotics over the last couple years. That's because, for the first time since the 1961 debut of GM's Unimate, regarded as the first industrial robot, the field is once again transforming world economies. Only this time the impact is going to be broader. That's particularly true in light of the COVID-19 pandemic, which has helped advance automation adoption across a variety of industries as manufacturers, fulfillment centers, retail, and restaurants seek to create durable, hygienic operations that can withstand evolving disruptions and regulations.

This week at CES 2019, UBTECH Robotics (which was valued at $5 billion as of mid-2018) is announcing a major update to a walking robot first demonstrated at CES 2018. UBTECH's Walker has gained a torso, arms, hands, and a head, and is now as humanoid as bipedal robots get. UBTECH has posted a couple of new videos, and answered some questions about Walker's capabilities and where our expectations should be. "Walker is your agile smart companion--an intelligent, bipedal humanoid robot that aims to one day be an indispensable part of your family. Standing 4.75 feet (1.45 m) tall and weighing 170 lbs (77 kg), the new version of Walker is more advanced than ever, including arms and hands with the ability to grasp and manipulate objects, a refined torso with improved self-balancing, smooth and stable walking in difficult environments, and multi-modal interaction including voice, vision, and touch. Walker has 36 high-performance actuators and a full range of sensing systems that work together to insure smooth and fast walking."

Earlier this year, Diligent Robotics introduced a mobile manipulator called Poli, designed to take over non-care related, boring logistical tasks from overworked healthcare professionals who really should be doing better things with their time. Specifically, Diligent wants to automate things like bringing supplies from a central storage area to patient rooms, which sounds like it should be easy, but is actually very difficult. Autonomous mobile manipulation in semi-structured environments is hard at the best of times, and things get even harder in places like hospitals that are full of busy humans rushing around trying to save the lives of other humans. Over the past few months, Diligent has been busy iterating on the design of their robot, and they've made enough changes that it's no longer called Poli. It's a completely new robot, called Moxi.

To experience the state-of-the-art in autonomous mobile manipulation, you'll want to find some well-funded academic lab to visit. Or maybe check out Google, or Amazon, or Toyota Research, or drop in on the RoboCup@Home competition. Really, the only other place you're likely to find an autonomous mobile manipulator is in a relatively structured environment in a factory or warehouse, and even that is pretty rare. Mobile manipulation is super hard, especially when you try to do it in a less structured environment which may be full of all sorts of horribly unpredictable things (like humans). Diligent Robotics, a startup founded by Andrea Thomaz and Vivian Chu, is undaunted by the challenge of autonomous mobile manipulation in semi-structured environments.

Creating a successful robot company based around providing commercial services is not easy, although as of just the last few years, advances in robotics technology has at least made it possible. Companies like Savioke have shown that robotics has reached a point where autonomous platforms can operate in semi-structured environments, doing useful tasks reliably and cost effectively enough to make a compelling business case. Luvozo, a startup founded in 2013 and based in College Park, Md., is bringing autonomous robots to semi-structured environments with an enormous amount of potential: skilled nursing facilities for seniors. They're introducing a "robot concierge" called SAM, designed to "provide frequent check-ins and non-medical care for residents in long-term care settings" through autonomous navigation, telepresence, and an innovative fall hazard detection system. The potential market here is enormous, and to find out more, we stopped by Luvozo and spoke with CEO and co-founder David Pietrocola.

Earlier Teamwork implies communication with shared references work also evaluates the robustness of ICP against low constrained and symbols. The collaboration between robot and human is environments (Rusinkiewicz and Levoy 2001). This therefore highly dependent on a common representation of was mainly done in simulation so real word datasets targeting the environment. Part of this representation is a map, either this limitations could bring the analysis farther. An other global or local, that can serve both the robot to do its own problem, recently raised in vision registration (Mortensen, task and the human to increase his situation awareness, to Deng, and Shapiro 2005), is the problem of repetitive elements collaboratively plan and observe the evolution of a situation.