Monday, November 4th, 2019

Time	Event
12:00a	Technique helps robots find the front door In the not too distant future, robots may be dispatched as last-mile delivery vehicles to drop your takeout order, package, or meal-kit subscription at your doorstep — if they can find the door. Standard approaches for robotic navigation involve mapping an area ahead of time, then using algorithms to guide a robot toward a specific goal or GPS coordinate on the map. While this approach might make sense for exploring specific environments, such as the layout of a particular building or planned obstacle course, it can become unwieldy in the context of last-mile delivery. Imagine, for instance, having to map in advance every single neighborhood within a robot’s delivery zone, including the configuration of each house within that neighborhood along with the specific coordinates of each house’s front door. Such a task can be difficult to scale to an entire city, particularly as the exteriors of houses often change with the seasons. Mapping every single house could also run into issues of security and privacy. Now MIT engineers have developed a navigation method that doesn’t require mapping an area in advance. Instead, their approach enables a robot to use clues in its environment to plan out a route to its destination, which can be described in general semantic terms, such as “front door” or “garage,” rather than as coordinates on a map. For example, if a robot is instructed to deliver a package to someone's front door, it might start on the road and see a driveway, which it has been trained to recognize as likely to lead toward a sidewalk, which in turn is likely to lead to the front door. The new technique can greatly reduce the time a robot spends exploring a property before identifying its target, and it doesn’t rely on maps of specific residences.  “We wouldn’t want to have to make a map of every building that we’d need to visit,” says Michael Everett, a graduate student in MIT’s Department of Mechanical Engineering. “With this technique, we hope to drop a robot at the end of any driveway and have it find a door.” Everett will present the group’s results this week at the International Conference on Intelligent Robots and Systems. The paper, which is co-authored by Jonathan How, professor of aeronautics and astronautics at MIT, and Justin Miller of the Ford Motor Company, is a finalist for “Best Paper for Cognitive Robots.” “A sense of what things are” In recent years, researchers have worked on introducing natural, semantic language to robotic systems, training robots to recognize objects by their semantic labels, so they can visually process a door as a door, for example, and not simply as a solid, rectangular obstacle. “Now we have an ability to give robots a sense of what things are, in real-time,” Everett says. Everett, How, and Miller are using similar semantic techniques as a springboard for their new navigation approach, which leverages pre-existing algorithms that extract features from visual data to generate a new map of the same scene, represented as semantic clues, or context. In their case, the researchers used an algorithm to build up a map of the environment as the robot moved around, using the semantic labels of each object and a depth image. This algorithm is called semantic SLAM (Simultaneous Localization and Mapping). While other semantic algorithms have enabled robots to recognize and map objects in their environment for what they are, they haven’t allowed a robot to make decisions in the moment while navigating a new environment, on the most efficient path to take to a semantic destination such as a “front door.” “Before, exploring was just, plop a robot down and say ‘go,’ and it will move around and eventually get there, but it will be slow,” How says. The cost to go The researchers looked to speed up a robot’s path-planning through a semantic, context-colored world. They developed a new “cost-to-go estimator,” an algorithm that converts a semantic map created by preexisting SLAM algorithms into a second map, representing the likelihood of any given location being close to the goal. “This was inspired by image-to-image translation, where you take a picture of a cat and make it look like a dog,” Everett says. “The same type of idea happens here where you take one image that looks like a map of the world, and turn it into this other image that looks like the map of the world but now is colored based on how close different points of the map are to the end goal.” This cost-to-go map is colorized, in gray-scale, to represent darker regions as locations far from a goal, and lighter regions as areas that are close to the goal. For instance, the sidewalk, coded in yellow in a semantic map, might be translated by the cost-to-go algorithm as a darker region in the new map, compared with a driveway, which is progressively lighter as it approaches the front door — the lightest region in the new map. The researchers trained this new algorithm on satellite images from Bing Maps containing 77 houses from one urban and three suburban neighborhoods. The system converted a semantic map into a cost-to-go map, and mapped out the most efficient path, following lighter regions in the map, to the end goal. For each satellite image, Everett assigned semantic labels and colors to context features in a typical front yard, such as grey for a front door, blue for a driveway, and green for a hedge. During this training process, the team also applied masks to each image to mimic the partial view that a robot’s camera would likely have as it traverses a yard. “Part of the trick to our approach was [giving the system] lots of partial images,” How explains. “So it really had to figure out how all this stuff was interrelated. That’s part of what makes this work robustly.” The researchers then tested their approach in a simulation of an image of an entirely new house, outside of the training dataset, first using the preexisting SLAM algorithm to generate a semantic map, then applying their new cost-to-go estimator to generate a second map, and path to a goal, in this case, the front door. The group’s new cost-to-go technique found the front door 189 percent faster than classical navigation algorithms, which do not take context or semantics into account, and instead spend excessive steps exploring areas that are unlikely to be near their goal. Everett says the results illustrate how robots can use context to efficiently locate a goal, even in unfamiliar, unmapped environments. “Even if a robot is delivering a package to an environment it’s never been to, there might be clues that will be the same as other places it’s seen,” Everett says. “So the world may be laid out a little differently, but there’s probably some things in common.” This research is supported, in part, by the Ford Motor Company. (Comment on this)
12:44p	Better autonomous “reasoning” at tricky intersections MIT and Toyota researchers have designed a new model to help autonomous vehicles determine when it’s safe to merge into traffic at intersections with obstructed views. Navigating intersections can be dangerous for driverless cars and humans alike. In 2016, roughly 23 percent of fatal and 32 percent of nonfatal U.S. traffic accidents occurred at intersections, according to a 2018 Department of Transportation study. Automated systems that help driverless cars and human drivers steer through intersections can require direct visibility of the objects they must avoid. When their line of sight is blocked by nearby buildings or other obstructions, these systems can fail. The researchers developed a model that instead uses its own uncertainty to estimate the risk of potential collisions or other traffic disruptions at such intersections. It weighs several critical factors, including all nearby visual obstructions, sensor noise and errors, the speed of other cars, and even the attentiveness of other drivers. Based on the measured risk, the system may advise the car to stop, pull into traffic, or nudge forward to gather more data. “When you approach an intersection there is potential danger for collision. Cameras and other sensors require line of sight. If there are occlusions, they don’t have enough visibility to assess whether it’s likely that something is coming,” says Daniela Rus, director of the Computer Science and Artificial Intelligence Laboratory (CSAIL) and the Andrew and Erna Viterbi Professor of Electrical Engineering and Computer Science. “In this work, we use a predictive-control model that’s more robust to uncertainty, to help vehicles safely navigate these challenging road situations.” The researchers tested the system in more than 100 trials of remote-controlled cars turning left at a busy, obstructed intersection in a mock city, with other cars constantly driving through the cross street. Experiments involved fully autonomous cars and cars driven by humans but assisted by the system. In all cases, the system successfully helped the cars avoid collision from 70 to 100 percent of the time, depending on various factors. Other similar models implemented in the same remote-control cars sometimes couldn’t complete a single trial run without a collision. Joining Rus on the paper are: first author Stephen G. McGill, Guy Rosman, and Luke Fletcher of the Toyota Research Institute (TRI); graduate students Teddy Ort and Brandon Araki, researcher Alyssa Pierson, and postdoc Igor Gilitschenski, all of CSAIL; Sertac Karaman, an MIT associate professor of aeronautics and astronautics; and John J. Leonard, the Samuel C. Collins Professor of Mechanical and Ocean Engineering of MIT and a TRI technical advisor. Modeling road segments The model is specifically designed for road junctions in which there is no stoplight and a car must yield before maneuvering into traffic at the cross street, such as taking a left turn through multiple lanes or roundabouts. In their work, the researchers split a road into small segments. This helps the model determine if any given segment is occupied to estimate a conditional risk of collision. Autonomous cars are equipped with sensors that measure the speed of other cars on the road. When a sensor clocks a passing car traveling into a visible segment, the model uses that speed to predict the car’s progression through all other segments. A probabilistic “Bayesian network” also considers uncertainties — such as noisy sensors or unpredictable speed changes — to determine the likelihood that each segment is occupied by a passing car. Because of nearby occlusions, however, this single measurement may not suffice. Basically, if a sensor can’t ever see a designated road segment, then the model assigns it a high likelihood of being occluded. From where the car is positioned, there’s increased risk of collision if the car just pulls out fast into traffic. This encourages the car to nudge forward to get a better view of all occluded segments. As the car does so, the model lowers its uncertainty and, in turn, risk. But even if the model does everything correctly, there’s still human error, so the model also estimates the awareness of other drivers. “These days, drivers may be texting or otherwise distracted, so the amount of time it takes to react may be a lot longer,” McGill says. “We model that conditional risk, as well.” That depends on computing the probability that a driver saw or didn’t see the autonomous car pulling into the intersection. To do so, the model looks at the number of segments a traveling car has passed through before the intersection. The more segments it had occupied before reaching the intersection, the higher the likelihood it has spotted the autonomous car and the lower the risk of collision. The model sums all risk estimates from traffic speed, occlusions, noisy sensors, and driver awareness. It also considers how long it will take the autonomous car to steer a preplanned path through the intersection, as well as all safe stopping spots for crossing traffic. This produces a total risk estimate. That risk estimate gets updated continuously for wherever the car is located at the intersection. In the presence of multiple occlusions, for instance, it’ll nudge forward, little by little, to reduce uncertainty. When the risk estimate is low enough, the model tells the car to drive through the intersection without stopping. Lingering in the middle of the intersection for too long, the researchers found, also increases risk of a collision. Assistance and intervention Running the model on remote-control cars in real-time indicates that it’s efficient and fast enough to deploy into full-scale autonomous test cars in the near future, the researchers say. (Many other models are too computationally heavy to run on those cars.) The model still needs far more rigorous testing before being used for real-world implementation in production vehicles. The model would serve as a supplemental risk metric that an autonomous vehicle system can use to better reason about driving through intersections safely. The model could also potentially be implemented in certain “advanced driver-assistive systems” (ADAS), where humans maintain shared control of the vehicle. Next, the researchers aim to include other challenging risk factors in the model, such as the presence of pedestrians in and around the road junction. (Comment on this)
2:54p	Autonomous system improves environmental sampling at sea An autonomous robotic system invented by researchers at MIT and the Woods Hole Oceanographic Institution (WHOI) efficiently sniffs out the most scientifically interesting — but hard-to-find — sampling spots in vast, unexplored waters. Environmental scientists are often interested in gathering samples at the most interesting locations, or “maxima,” in an environment. One example could be a source of leaking chemicals, where the concentration is the highest and mostly unspoiled by external factors. But a maximum can be any quantifiable value that researchers want to measure, such as water depth or parts of coral reef most exposed to air. Efforts to deploy maximum-seeking robots suffer from efficiency and accuracy issues. Commonly, robots will move back and forth like lawnmowers to cover an area, which is time-consuming and collects many uninteresting samples. Some robots sense and follow high-concentration trails to their leak source. But they can be misled. For example, chemicals can get trapped and accumulate in crevices far from a source. Robots may identify those high-concentration spots as the source yet be nowhere close. In a paper being presented at the International Conference on Intelligent Robots and Systems (IROS), the researchers describe “PLUMES,” a system that enables autonomous mobile robots to zero in on a maximum far faster and more efficiently. PLUMES leverages probabilistic techniques to predict which paths are likely to lead to the maximum, while navigating obstacles, shifting currents, and other variables. As it collects samples, it weighs what it’s learned to determine whether to continue down a promising path or search the unknown — which may harbor more valuable samples. Importantly, PLUMES reaches its destination without ever getting trapped in those tricky high-concentration spots. “That’s important, because it’s easy to think you’ve found gold, but really you’ve found fool’s gold,” says co-first author Victoria Preston, a PhD student in the Computer Science and Artificial Intelligence Laboratory (CSAIL) and in the MIT-WHOI Joint Program. The researchers built a PLUMES-powered robotic boat that successfully detected the most exposed coral head in the Bellairs Fringing Reef in Barbados — meaning, it was located in the shallowest spot — which is useful for studying how sun exposure impacts coral organisms. In 100 simulated trials in diverse underwater environments, a virtual PLUMES robot also consistently collected seven to eight times more samples of maxima than traditional coverage methods in allotted time frames. “PLUMES does the minimal amount of exploration necessary to find the maximum and then concentrates quickly on collecting valuable samples there,” says co-first author Genevieve Flaspohler, a PhD student and in CSAIL and the MIT-WHOI Joint Program. Joining Preston and Flaspohler on the paper are: Anna P.M. Michel and Yogesh Girdhar, both scientists in the Department of Applied Ocean Physics and Engineering at the WHOI; and Nicholas Roy, a professor in CSAIL and in the Department of Aeronautics and Astronautics.   Navigating an exploit-explore tradeoff A key insight of PLUMES was using techniques from probability to reason about navigating the notoriously complex tradeoff between exploiting what’s learned about the environment and exploring unknown areas that may be more valuable. “The major challenge in maximum-seeking is allowing the robot to balance exploiting information from places it already knows to have high concentrations and exploring places it doesn’t know much about,” Flaspohler says. “If the robot explores too much, it won’t collect enough valuable samples at the maximum. If it doesn’t explore enough, it may miss the maximum entirely.” Dropped into a new environment, a PLUMES-powered robot uses a probabilistic statistical model called a Gaussian process to make predictions about environmental variables, such as chemical concentrations, and estimate sensing uncertainties. PLUMES then generates a distribution of possible paths the robot can take, and uses the estimated values and uncertainties to rank each path by how well it allows the robot to explore and exploit. At first, PLUMES will choose paths that randomly explore the environment. Each sample, however, provides new information about the targeted values in the surrounding environment — such as spots with highest concentrations of chemicals or shallowest depths. The Gaussian process model exploits that data to narrow down possible paths the robot can follow from its given position to sample from locations with even higher value. PLUMES uses a novel objective function — commonly used in machine-learning to maximize a reward — to make the call of whether the robot should exploit past knowledge or explore the new area. “Hallucinating” paths The decision where to collect the next sample relies on the system’s ability to “hallucinate” all possible future action from its current location. To do so, it leverages a modified version of Monte Carlo Tree Search (MCTS), a path-planning technique popularized for powering artificial-intelligence systems that master complex games, such as Go and Chess. MCTS uses a decision tree — a map of connected nodes and lines — to simulate a path, or sequence of moves, needed to reach a final winning action. But in games, the space for possible paths is finite. In unknown environments, with real-time changing dynamics, the space is effectively infinite, making planning extremely difficult. The researchers designed “continuous-observation MCTS,” which leverages the Gaussian process and the novel objective function to search over this unwieldy space of possible real paths. The root of this MCTS decision tree starts with a “belief” node, which is the next immediate step the robot can take. This node contains the entire history of the robot’s actions and observations up until that point. Then, the system expands the tree from the root into new lines and nodes, looking over several steps of future actions that lead to explored and unexplored areas. Then, the system simulates what would happen if it took a sample from each of those newly generated nodes, based on some patterns it has learned from previous observations. Depending on the value of the final simulated node, the entire path receives a reward score, with higher values equaling more promising actions. Reward scores from all paths are rolled back to the root node. The robot selects the highest-scoring path, takes a step, and collects a real sample. Then, it uses the real data to update its Gaussian process model and repeats the “hallucination” process. “As long as the system continues to hallucinate that there may be a higher value in unseen parts of the world, it must keep exploring,” Flaspohler says. “When it finally converges on a spot it estimates to be the maximum, because it can’t hallucinate a higher value along the path, it then stops exploring.” Now, the researchers are collaborating with scientists at WHOI to use PLUMES-powered robots to localize chemical plumes at volcanic sites and study methane releases in melting coastal estuaries in the Arctic. Scientists are interested in the source of chemical gases released into the atmosphere, but these test sites can span hundreds of square miles. “They can [use PLUMES to] spend less time exploring that huge area and really concentrate on collecting scientifically valuable samples,” Preston says. (Comment on this)
3:01p	Chemists observe “spooky” quantum tunneling A molecule of ammonia, NH3, typically exists as an umbrella shape, with three hydrogen atoms fanned out in a nonplanar arrangement around a central nitrogen atom. This umbrella structure is very stable and would normally be expected to require a large amount of energy to be inverted. However, a quantum mechanical phenomenon called tunneling allows ammonia and other molecules to simultaneously inhabit geometric structures that are separated by a prohibitively high energy barrier. A team of chemists that includes Robert Field, the Robert T. Haslam and Bradley Dewey Professor of Chemistry at MIT, has examined this phenomenon by using a very large electric field to suppress the simultaneous occupation of ammonia molecules in the normal and inverted states. “It’s a beautiful example of the tunneling phenomenon, and it reveals a wonderful strangeness of quantum mechanics,” says Field, who is one of the senior authors of the study. Heon Kang, a professor of chemistry at Seoul National University, is also a senior author of the study, which appears this week in the Proceedings of the National Academy of Sciences. Youngwook Park and Hani Kang of Seoul National University are also authors of the paper. Suppressing inversion The experiments, performed at Seoul National University, were enabled by the researchers’ new method for applying a very large electric field (up to 200,000,000 volts per meter) to a sample sandwiched between two electrodes. This assembly is only a few hundred nanometers thick, and the electric field applied to it generates forces nearly as strong as the interactions between adjacent molecules. “We can apply these huge fields, which are almost the same magnitude as the fields that two molecules experience when they approach each other,” Field says. “That means we’re using an external means to operate on an equal playing field with what the molecules can do themselves.” This allowed the researchers to explore quantum tunneling, a phenomenon often used in undergraduate chemistry courses to demonstrate one of the “spookinesses” of quantum mechanics, Field says. As an analogy, imagine you are hiking in a valley. To reach the next valley, you need to climb a large mountain, which requires a lot of work. Now, imagine that you could tunnel through the mountain to get to the next valley, with no real effort required. This is what quantum mechanics allows, under certain conditions. In fact, if the two valleys have exactly the same shape, you would be simultaneously located in both valleys. In the case of ammonia, the first valley is the low-energy, stable umbrella state. For the molecule to reach the other valley — the inverted state, which has exactly the same low-energy — classically it would need to ascend into a very high-energy state. However, quantum mechanically, the isolated molecule exists with equal probability in both valleys. Under quantum mechanics, the possible states of a molecule, such as ammonia, are described in terms of a characteristic energy level pattern.  The molecule initially exists in either the normal or inverted structure, but it can tunnel spontaneously to the other structure. The amount of time required for that tunneling to occur is encoded in the energy level pattern. If the barrier between the two structures is high, the tunneling time is long. Under certain circumstances, such as application of a strong electric field, tunneling between the regular and inverted structures can be suppressed. For ammonia, exposure to a strong electric field lowers the energy of one structure and raises the energy of the other (inverted) structure. As a result, all of the ammonia molecules can be found in the lower energy state. The researchers demonstrated this by creating a layered argon-ammonia-argon structure at 10 kelvins. Argon is an inert gas which is solid at 10 K, but the ammonia molecules can rotate freely in the argon solid. As the electric field is increased, the energy states of the ammonia molecules change in such a way that the probabilities of finding the molecules in the normal and inverted states become increasingly far apart, and tunneling can no longer occur. This effect is completely reversible and nondestructive: As the electric field is decreased, the ammonia molecules return to their normal state of being simultaneously in both wells. “This manuscript describes a burgeoning frontier in our ability to tame molecules and control their underlying dynamics,” says Patrick Vaccaro, a professor of chemistry at Yale University who was not involved in the study. “The experimental approach set forth in this paper is unique, and it has enormous ramifications for future efforts to interrogate molecular structure and dynamics, with the present application affording fundamental insights into the nature of tunneling-mediated phenomena.” Lowering the barriers For many molecules, the barrier to tunneling is so high that tunneling would never happen during the lifespan of the universe, Field says. However, there are molecules other than ammonia that can be induced to tunnel by careful tuning of the applied electric field. His colleagues are now working on exploiting this approach with some of those molecules. “Ammonia is special because of its high symmetry and the fact that it’s probably the first example anybody would ever discuss from a chemical point of view of tunneling,” Field says. “However, there are many examples where this could be exploited. The electric field, because it’s so large, is capable of acting on the same scale as the actual chemical interactions,” offering a powerful way of externally manipulating molecular dynamics. The research was funded by the Samsung Science and Technology Foundation and the National Science Foundation. (Comment on this)

<< Previous Day

2019/11/04 [Calendar]

Next Day >>