Offices of the future will forgo open cubicles for'sentient' pods that adjust the indoor environment the moment you step inside and close the door. I ventured outside my home office to try out what is deemed'the work from home killer,' finding the structure was packed with the lasted tech, including software used in self-driving cars. Sitting down in the 4G-connected Smart Pod, ventilation automatically started up, flushing air through the pod every minute, and lights instantly adjusted based on the surrounding illumination. While the pods feature glass sidings to provide a window to the outside world, the inside was incredibly quiet - you could hear a pin drop. Framery, the mastermind behind the plan to get employees back into office, offers several options for staff - from a pod with a single desk to a table that seats four and a larger meeting room for around six employees.

Not so long ago it may have seemed more like a futuristic vision of the workplace – or a hospital. But the hands-free door handles, self-cleaning surfaces, antimicrobial paint, air-monitoring display tools, UV light disinfection robots, and 135 other measures at an office block in Bucharest are here to stay, say the creators behind what they are touting as one of the world's most virus-resilient workplaces, which they hope will become the new normal in office design. Entering H3, a five-storey building in a western neighbourhood of the Romanian capital, is like learning the steps to a new dance. A flick of the wrist opens the door, and a red line marks the spot at which to stand from where a thermal body camera 2 metres away scans arrivals for signs of fever. Those who are "green-lighted" can follow the tracks to the self-clean lift, step on one of two foot pads and be transported through the building, safe in the knowledge that a UV lighting disinfection system installed in the ventilation shafts is keeping them infection-free between floors. Anyone whose head flashes red on the screen, however, is whisked away by a plastic-gloved "immune steward" into a nearby quarantine room: a glass box with a panic button and its own internal ventilation system shut off from the rest of the building.

We present an integrated Task-Motion Planning (TMP) framework for navigation in large-scale environments. Of late, TMP for manipulation has attracted significant interest resulting in a proliferation of different approaches. In contrast, TMP for navigation has received considerably less attention. Autonomous robots operating in real-world complex scenarios require planning in the discrete (task) space and the continuous (motion) space. In knowledge-intensive domains, on the one hand, a robot has to reason at the highest-level, for example, the objects to procure, the regions to navigate to in order to acquire them; on the other hand, the feasibility of the respective navigation tasks have to be checked at the execution level. This presents a need for motion-planning-aware task planners. In this paper, we discuss a probabilistically complete approach that leverages this task-motion interaction for navigating in large knowledge-intensive domains, returning a plan that is optimal at the task-level. The framework is intended for motion planning under motion and sensing uncertainty, which is formally known as belief space planning. The underlying methodology is validated in simulation, in an office environment and its scalability is tested in the larger Willow Garage world. A reasonable comparison with a work that is closest to our approach is also provided. We also demonstrate the adaptability of our approach by considering a building floor navigation domain. Finally, we also discuss the limitations of our approach and put forward suggestions for improvements and future work.

We consider problems of making sequences of decisions to accomplish tasks, interacting via the medium of language. These problems are often tackled with reinforcement learning approaches. We find that these models do not generalize well when applied to novel task domains. However, the large amount of computation necessary to adequately train and explore the search space of sequential decision making, under a reinforcement learning paradigm, precludes the inclusion of large contextualized language models, which might otherwise enable the desired generalization ability. We introduce a teacher-student imitation learning methodology and a means of converting a reinforcement learning model into a natural language understanding model. Together, these methodologies enable the introduction of contextualized language models into the sequential decision making problem space. We show that models can learn faster and generalize more, leveraging both the imitation learning and the reformulation. Our models exceed teacher performance on various held-out decision problems, by up to 7% on in-domain problems and 24% on out-of-domain problems.

Coverage path planning is a well-studied problem in robotics in which a robot must plan a path that passes through every point in a given area repeatedly, usually with a uniform frequency. To address the scenario in which some points need to be visited more frequently than others, this problem has been extended to non-uniform coverage planning. This paper considers the variant of non-uniform coverage in which the robot does not know the distribution of relevant events beforehand and must nevertheless learn to maximize the rate of detecting events of interest. This continual area sweeping problem has been previously formalized in a way that makes strong assumptions about the environment, and to date only a greedy approach has been proposed. We generalize the continual area sweeping formulation to include fewer environmental constraints, and propose a novel approach based on reinforcement learning in a Semi-Markov Decision Process. This approach is evaluated in an abstract simulation and in a high fidelity Gazebo simulation. These evaluations show significant improvement upon the existing approach in general settings, which is especially relevant in the growing area of service robotics.

The cubicle is making a comeback. As thousands of companies contemplate restarting operations, executives are weighing how best to reconfigure workspaces that have, by and large, been designed to minimize cost and foster the face-to-face interactions that can spread the deadly coronavirus. Some companies are looking at high-tech approaches to enforce social distancing and track interactions, with location-monitoring apps and badges, artificial intelligence surveillance cameras, and high-tech health checks. Other innovations will be simpler: stickers to enforce 6 feet of distance between coworkers; staggered shifts that allow for more spacing; more regular cleanings; and of course oodles of hand sanitizer. But one of the most important innovations may turn out to be cardboard or plastic dividers that turn open-plan offices into something more reminiscent of the 1980s.

Facial recognition has been used for a wide range of hi-tech applications in China – from airport security clearance to crime prevention. Now it is being used to solve a more down-to-earth problem. On Shamian island, a popular historical tourist attraction in Guangzhou, facial recognition for toilet paper dispensing has been introduced in some cubicles, according to a report in the Guangzhou-based Information Times. Users can remove 90cm of toilet paper after their face is recognized. If the system detects the same face twice within 10 minutes, no further paper will be dispensed.

It wasn't too long ago work looked like exactly what you would expect: an open office space with desks and/or cubicles lining the walls or throughout the space. Conference rooms were nearby and the break room was always bustling. The people in charge were older and more experienced. Those lower on the ladder were younger and focused. Some were climbing the corporate ladder while others held it in place for them.

According to mainstream video games, modern warfare is all about cyborg arms, laser shields and jarheads blowing up baddies under the guidance of recognisable character actors. However, the frenetic antics of the Call of Duty series and its ilk are behind the times. The drone pilot protagonist of 2012's free indie game Unmanned is a more accurate representation of a modern soldier: a man who plays video games with his son every weekend, and who has also killed countless foreigners from a grey-walled cubicle in Nevada. You play an American warrior, square of jaw and beefy of build, who works from an office out in the desert. A click of his mouse sends tons of missile plummeting from anonymous drone planes with an eerie blank space where you'd expect to see a cockpit.

The future has arrived and it's your first day at your new job. You step across the threshold sporting a nervous smile and harboring visions of virtual handshakes and brain-computer interfaces. After all, this is one of those newfangled, modern offices that science-fiction writers have been dreaming up for ages. No, it's not one of the ubiquitous glass walls, but the harsh reality of an office that, at first glance, doesn't appear much different from what you're accustomed to. A kitchenette stocked with stale donuts lurks in the background. And, by the way, you were fifteen minutes late because the commute is still hell.