MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) wants to convert laser cutters into something more. By attaching a head to a commercial laser cutter and adding software, they combine the functions of a cutter, a conductive printer, and a pick and place system. The idea is to enable construction of entire devices such as robots and drones.
The concept, called LaserFactory, sounds like a Star Trek-style replicator, but it doesn’t create things like circuit elements and motors. It simply picks them up, places them, and connects them using silver conductive ink. You can get a good idea of how it works by watching the video below.
What do you do when you have to disinfect an entire warehouse? You could send a group of people through the place with UV-C lamps, but that would take a long time as said humans cannot be in the same area as the UV-C radiation, as much as they may like the smell of BBQ chicken. Constantly repositioning the lamps or installing countless lamps would get in the way during normal operation. The answer is to strap UV-C lights to a robot according to MIT’s CSAIL, and have it ride around the space.
As can be seen in the video (also embedded after the break), a CSAIL group has been working with telepresence robotics company Ava Robotics and the Greater Boston Food Bank (GBFB). Their goal was to create a robotic system that could autonomously disinfect a GBFB warehouse using UV-C without exposing any humans to the harmful radiation. While the robotics can be controlled remotely, they can also map the space and navigate between waypoints.
While testing the system, the team used a UV-C dosimeter to confirm the effectiveness of this setup. With the robot driving along at a leisurely 0.22 miles per hour (~0.35 kilometer per hour), it was able to cover approximately 4,000 square feet (~372 square meter) in about half an hour. They estimated that about 90% of viruses like SARS-CoV-2 could be neutralized this way.
During trial runs, they discovered the need to have the robot adapt to the constantly changing layout of the warehouse, including which aisles require which UV-C depending on how full they are. Having multiple of these robots in the same space coordinate with each other would also be a useful feature addition.
Most often, humans and robots do not have to work directly together, instead working on different parts in a production pipeline or with the robot performing tasks instead of a human. In such cases any human-robot interaction (HRI) will be superficial. Yet what if humans and robots have to work alongside each other? This is a question which a group of students at MIT’s Computer Science and Artificial Intelligence Lab (CSAIL) have recently studied some answers to.
In their paper on human-robot collaborative tasks (PDF), they cover the three possible models one can use for this kind of interaction: there can be no communication (‘silent’), the communication can be pre-programmed (state machine), or in this case a Markov model-based system. This framework which they demonstrate is called CommPlan and it uses observation data from human subjects to construct a Markov model that can integrate sensor data in order to decide on its next action.
In the experiment they performed (the preparation of a meal; see the embedded video after the break), human subjects had to work alongside a robot. Between the three different approaches, the CommPlan one was the fastest, using voice interaction only when it deemed it to be necessary. The experiment’s subjects expressed hereby a preference for bidirectional communication, much as would occur between human workers.
Twenty years ago, a cryptographic puzzle was included in the construction of a building on the MIT campus. The structure that houses what is now MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) includes a time capsule designed by the building’s architect, [Frank Gehry]. It contains artifacts related to the history of computing, and was meant to be opened whenever someone solved a cryptographic puzzle, or after 35 years had elapsed.
The famous cryptographer, [Ronald Rivest], put together what we now know is a deceptively simple challenge. It involves a successive squaring operation, and since it is inherently sequential there is no possibility of using parallel computing techniques to take any shortcuts. [Fabrot] used the GNU Multiple Precision Arithmetic Library in his code, and took over 3 years of computing time to solve it. Meanwhile another team is using an FPGA and are expecting a solution in months, though have been pipped to the post by the Belgian.
The original specification document is a fascinating read, for both the details of the puzzle itself and for [Rivest]’s predictions as to the then future direction of computing power. He expected the puzzle would take the full 35 years to solve and that there would be 10Ghz processors by 2012 when Moore’s Law would begin to tail off, but he is reported as saying that he underestimated the corresponding advances in software.
Header image: Ray and Maria Stata Center, Tafyrn (CC BY 3.0)
Recycling is on paper at least, a wonderful thing. Taking waste and converting it into new usable material is generally more efficient than digging up more raw materials. Unfortunately though, sorting this waste material is a labor-intensive process. With China implementing bans on waste imports, suddenly the world is finding it difficult to find anywhere to accept its waste for reprocessing. In an attempt to help solve this problem, MIT’s CSAIL group have developed a recycling robot.
The robot aims to reduce the reliance on human sorters and thus improve the viability of recycling operations. This is achieved through a novel approach of using special actuators that sort by material stiffness and conductivity. The actuators are known as handed shearing auxetics – a type of actuator that expands in width when stretched. By having two of these oppose each other, they can grip a variety of objects without having to worry about orientation or grip strength like conventional rigid grippers. With pressure sensors to determine how much a material squishes, and a capacitive sensor to determine conductivity, it’s possible to sort materials into paper, plastic, and metal bins.
The research paper outlines the development of the gripper in detail. Care was taken to build something that is robust enough to deal with the recycling environment, as well as capable of handling the sorting tasks. There’s a long way to go to take this proof of concept to the commercially viable stage, but it’s a promising start to a difficult resource problem.
Robot design traditionally separates the body geometry from the mechanics of the gait, but they both have a profound effect upon one another. What if you could play with both at once, and crank out useful prototypes cheaply using just about any old 3D printer? That’s where Interactive Robogami comes in. It’s a tool from MIT’s Computer Science and Artificial Intelligence Laboratory (CSAIL) that aims to let people design, simulate, and then build simple robots with a “3D print, then fold” approach. The idea behind the system is partly to take advantage of the rapid prototyping afforded by 3D printers, but mainly it’s to change how the design work is done.
To make a robot, the body geometry and limb design are all done and simulated in the Robogami tool, where different combinations can have a wild effect on locomotion. Once a design is chosen, the end result is a 3D printable flat pack which is then assembled into the final form with a power supply, Arduino, and servo motors.
A white paper is available online and a demonstration video is embedded below. It’s debatable whether these devices on their own qualify as “robots” since they have no sensors, but as a tool to quickly prototype robot body geometries and gaits it’s an excitingly clever idea.
There are a lot of ways to try to mathematically quantify how healthy a person is. Things like resting pulse rate, blood pressure, and blood oxygenation are all quite simple to measure and can be used to predict various clinical outcomes. However, one you may not have considered is gait velocity, or the speed at which a person walks. It turns out gait velocity is a viable way to predict the onset of a wide variety of conditions, such as congestive heart failure or chronic obtrusive pulmonary disease. It turns out, as people become sick, elderly or infirm, they tend to walk slower – just like the little riflemen in your favourite RTS when their healthbar’s way in the red. But how does one measure this? MIT’s CSAIL has stepped up, with a way to measure walking speed completely wirelessly.
You can read the paper here (PDF). The WiGate device sends out a low-power radio signal, and then measures the reflections to determine a person’s location over time. Alone, however, this is not enough – it’s important to measure the walking speed specifically, to avoid false positives being triggered by a person simply not moving while watching television, for example. Algorithms are used to separate walking activity from the data set, allowing the device to sit in the background, recording walking speed data with no user interaction required whatsoever.
This form of passive monitoring could have great applications in nursing homes, where staff often have a huge number of patients to monitor. It would allow the collection of clinically relevant data without the need for any human intervention; the device could simply alert staff when a patient’s walking pattern is indicative of a bigger problem.