Humans are generally good at whole-body manipulation, but robots struggle with such tasks. To the robot, each spot where the box could touch any point on the carrier’s fingers, arms, and torso represents a contact event that it must reason about. With billions of potential contact events, planning for this task quickly becomes intractable.

Now MIT researchers found a way to simplify this process, known as contact-rich manipulation planning. They use an AI technique called smoothing, which summarizes many contact events into a smaller number of decisions, to enable even a simple algorithm to quickly identify an effective manipulation plan for the robot.

While still in its early days, this method could potentially enable factories to use smaller, mobile robots that can manipulate objects with their entire arms or bodies, rather than large robotic arms that can only grasp using fingertips. This may help reduce energy consumption and drive down costs. In addition, this technique could be useful in robots sent on exploration missions to Mars or other solar system bodies, since they could adapt to the environment quickly using only an onboard computer.

“Rather than thinking about this as a black-box system, if we can leverage the structure of these kinds of robotic systems using models, there is an opportunity to accelerate the whole procedure of trying to make these decisions and come up with contact-rich plans,” says H.J. Terry Suh, an electrical engineering and computer science (EECS) graduate student and co-lead author of a paper on this technique.

Joining Suh on the paper are co-lead author Tao Pang PhD ’23, a roboticist at Boston Dynamics AI Institute; Lujie Yang, an EECS graduate student; and senior author Russ Tedrake, the Toyota Professor of EECS, Aeronautics and Astronautics, and Mechanical Engineering, and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL). The research appears this week in IEEE Transactions on Robotics.

Learning about learning

Reinforcement learning is a machine-learning technique where an agent, like a robot, learns to complete a task through trial and error with a reward for getting closer to a goal. Researchers say this type of learning takes a black-box approach because the system must learn everything about the world through trial and error.

It has been used effectively for contact-rich manipulation planning, where the robot seeks to learn the best way to move an object in a specified manner.

But because there may be billions of potential contact points that a robot must reason about when determining how to use its fingers, hands, arms, and body to interact with an object, this trial-and-error approach requires a great deal of computation.

“Reinforcement learning may need to go through millions of years in simulation time to actually be able to learn a policy,” Suh adds.

On the other hand, if researchers specifically design a physics-based model using their knowledge of the system and the task they want the robot to accomplish, that model incorporates structure about this world that makes it more efficient.

Yet physics-based approaches aren’t as effective as reinforcement learning when it comes to contact-rich manipulation planning — Suh and Pang wondered why.

They conducted a detailed analysis and found that a technique known as smoothing enables reinforcement learning to perform so well.

Many of the decisions a robot could make when determining how to manipulate an object aren’t important in the grand scheme of things. For instance, each infinitesimal adjustment of one finger, whether or not it results in contact with the object, doesn’t matter very much. Smoothing averages away many of those unimportant, intermediate decisions, leaving a few important ones.

Reinforcement learning performs smoothing implicitly by trying many contact points and then computing a weighted average of the results. Drawing on this insight, the MIT researchers designed a simple model that performs a similar type of smoothing, enabling it to focus on core robot-object interactions and predict long-term behavior. They showed that this approach could be just as effective as reinforcement learning at generating complex plans.

“If you know a bit more about your problem, you can design more efficient algorithms,” Pang says.

A winning combination

Even though smoothing greatly simplifies the decisions, searching through the remaining decisions can still be a difficult problem. So, the researchers combined their model with an algorithm that can rapidly and efficiently search through all possible decisions the robot could make.

With this combination, the computation time was cut down to about a minute on a standard laptop.

They first tested their approach in simulations where robotic hands were given tasks like moving a pen to a desired configuration, opening a door, or picking up a plate. In each instance, their model-based approach achieved the same performance as reinforcement learning, but in a fraction of the time. They saw similar results when they tested their model in hardware on real robotic arms.

“The same ideas that enable whole-body manipulation also work for planning with dexterous, human-like hands. Previously, most researchers said that reinforcement learning was the only approach that scaled to dexterous hands, but Terry and Tao showed that by taking this key idea of (randomized) smoothing from reinforcement learning, they can make more traditional planning methods work extremely well, too,” Tedrake says.

However, the model they developed relies on a simpler approximation of the real world, so it cannot handle very dynamic motions, such as objects falling. While effective for slower manipulation tasks, their approach cannot create a plan that would enable a robot to toss a can into a trash bin, for instance. In the future, the researchers plan to enhance their technique so it could tackle these highly dynamic motions.

“If you study your models carefully and really understand the problem you are trying to solve, there are definitely some gains you can achieve. There are benefits to doing things that are beyond the black box,” Suh says.

This work is funded, in part, by Amazon, MIT Lincoln Laboratory, the National Science Foundation, and the Ocado Group.

Large spots are common features in the atmospheres of giant planets, the most famous being Jupiter’s Great Red Spot. On Neptune, a dark spot was first discovered by NASA’s Voyager 2 in 1989, before disappearing a few years later. “Since the first discovery of a dark spot, I’ve always wondered what these short-lived and elusive dark features are,” says Patrick Irwin, Professor at the University of Oxford in the UK and lead investigator of the study published today in Nature Astronomy.

Irwin and his team used data from ESO’s VLT to rule out the possibility that dark spots are caused by a ‘clearing’ in the clouds. The new observations indicate instead that dark spots are likely the result of air particles darkening in a layer below the main visible haze layer, as ices and hazes mix in Neptune’s atmosphere.

Coming to this conclusion was no easy feat because dark spots are not permanent features of Neptune’s atmosphere and astronomers had never before been able to study them in sufficient detail. The opportunity came after the NASA/ESA Hubble Space Telescope discovered several dark spots in Neptune’s atmosphere, including one in the planet’s northern hemisphere first noticed in 2018. Irwin and his team immediately got to work studying it from the ground — with an instrument that is ideally suited to these challenging observations.

Using the VLT’s Multi Unit Spectroscopic Explorer (MUSE), the researchers were able to split reflected sunlight from Neptune and its spot into its component colours, or wavelengths, and obtain a 3D spectrum [1]. This meant they could study the spot in more detail than was possible before. “I’m absolutely thrilled to have been able to not only make the first detection of a dark spot from the ground, but also record for the very first time a reflection spectrum of such a feature,” says Irwin.

Since different wavelengths probe different depths in Neptune’s atmosphere, having a spectrum enabled astronomers to better determine the height at which the dark spot sits in the planet’s atmosphere. The spectrum also provided information on the chemical composition of the different layers of the atmosphere, which gave the team clues as to why the spot appeared dark.

The observations also offered up a surprise result. “In the process we discovered a rare deep bright cloud type that had never been identified before, even from space,” says study co-author Michael Wong, a researcher at the University of California, Berkeley, USA. This rare cloud type appeared as a bright spot right beside the larger main dark spot, the VLT data showing that the new ‘deep bright cloud’ was at the same level in the atmosphere as the main dark spot. This means it is a completely new type of feature compared to the small ‘companion’ clouds of high-altitude methane ice that have been previously observed.

With the help of ESO’s VLT, it is now possible for astronomers to study features like these spots from Earth. “This is an astounding increase in humanity’s ability to observe the cosmos. At first, we could only detect these spots by sending a spacecraft there, like Voyager. Then we gained the ability to make them out remotely with Hubble. Finally, technology has advanced to enable this from the ground,” concludes Wong, before adding, jokingly: “This could put me out of work as a Hubble observer!“

Note

[1] MUSE is a 3D spectrograph that allows astronomers to observe the entirety of an astronomical object, like Neptune, in one go. At each pixel, the instrument measures the intensity of light as a function of its colour or wavelength. The resulting data form a 3D set in which each pixel of the image has a full spectrum of light. In total, MUSE measures over 3500 colours. The instrument is designed to take advantage of adaptive optics, which corrects for the turbulence in the Earth’s atmosphere, resulting in sharper images than otherwise possible. Without this combination of features, studying a Neptune dark spot from the ground would not have been possible.

“Patients should feel empowered to educate themselves about their medical conditions, but they should always discuss with a clinician, and resources on the Internet should not be consulted in isolation,” said corresponding author Danielle Bitterman, MD, of the Department of Radiation Oncology and the Artificial Intelligence in Medicine (AIM) Program of Mass General Brigham. “ChatGPT responses can sound a lot like a human and can be quite convincing. But, when it comes to clinical decision-making, there are so many subtleties for every patient’s unique situation. A right answer can be very nuanced, and not necessarily something ChatGPT or another large language model can provide.”

The emergence of artificial intelligence tools in health has been groundbreaking and has the potential to positively reshape the continuum of care. Mass General Brigham, as one of the nation’s top integrated academic health systems and largest innovation enterprises, is leading the way in conducting rigorous research on new and emerging technologies to inform the responsible incorporation of AI into care delivery, workforce support, and administrative processes.

Although medical decision-making can be influenced by many factors, Bitterman and colleagues chose to evaluate the extent to which ChatGPT’s recommendations aligned with the NCCN guidelines, which are used by physicians at institutions across the country. They focused on the three most common cancers (breast, prostate and lung cancer) and prompted ChatGPT to provide a treatment approach for each cancer based on the severity of the disease. In total, the researchers included 26 unique diagnosis descriptions and used four, slightly different prompts to ask ChatGPT to provide a treatment approach, generating a total of 104 prompts.

Nearly all responses (98 percent) included at least one treatment approach that agreed with NCCN guidelines. However, the researchers found that 34 percent of these responses also included one or more non-concordant recommendations, which were sometimes difficult to detect amidst otherwise sound guidance. A non-concordant treatment recommendation was defined as one that was only partially correct; for example, for a locally advanced breast cancer, a recommendation of surgery alone, without mention of another therapy modality. Notably, complete agreement in scoring only occurred in 62 percent of cases, underscoring both the complexity of the NCCN guidelines themselves and the extent to which ChatGPT’s output could be vague or difficult to interpret.

In 12.5 percent of cases, ChatGPT produced “hallucinations,” or a treatment recommendation entirely absent from NCCN guidelines. These included recommendations of novel therapies, or curative therapies for non-curative cancers. The authors emphasized that this form of misinformation can incorrectly set patients’ expectations about treatment and potentially impact the clinician-patient relationship.

Going forward, the researchers are exploring how well both patients and clinicians can distinguish between medical advice written by a clinician versus a large language model (LLM) like ChatGPT. They are also prompting ChatGPT with more detailed clinical cases to further evaluate its clinical knowledge.

The authors used GPT-3.5-turbo-0301, one of the largest models available at the time they conducted the study and the model class that is currently used in the open-access version of ChatGPT (a newer version, GPT-4, is only available with the paid subscription). They also used the 2021 NCCN guidelines, because GPT-3.5-turbo-0301 was developed using data up to September 2021. While results may vary if other LLMs and/or clinical guidelines are used, the researchers emphasize that many LLMs are similar in the way they are built and the limitations they possess.

“It is an open research question as to the extent LLMs provide consistent logical responses as oftentimes ‘hallucinations’ are observed,” said first author Shan Chen, MS, of the AIM Program. “Users are likely to seek answers from the LLMs to educate themselves on health-related topics — similarly to how Google searches have been used. At the same time, we need to raise awareness that LLMs are not the equivalent of trained medical professionals.”

Even as the field of human genomics forged ahead at an astonishing pace, the Y chromosome — one of the sex chromosomes — has long remained overlooked. It has been postulated that the human sex chromosomes once originated from a pair of structurally similar chromosomes, but subsequently one of the sex chromosomes, the ancestral Y chromosome, underwent significant degradation, losing 97%of its former complement of genes over many millions of years. This peculiar evolutionary trajectory has given rise to speculation that the human Y chromosomes might eventually disappear completely, albeit millions of years from now, and we already observe that some biological males do lose them in dividing cells as they age, with unclear health consequences.

In practical terms, the Y chromosome contains a large proportion of repetitive and heterochromatic (highly condensed, gene-poor and not transcribed to messenger RNA) sequences, making it exceptionally difficult to fully sequence. Using sequencing methods that can cover long, continuous sequences, the Telomere-to-Telomere (T2T) consortium has now published the first complete Y chromosome assembly from a single individual of European descent in “The complete sequence of a human Y chromosome” (Rhie et al. Nature). At the same time, a team led by Jackson Laboratory (JAX) Professor and The Robert Alvine Family Endowed Chair Charles Lee, Ph.D., FACMG, has assembled Y chromosomes from 43 unrelated males, with nearly half coming from African lineages in “Assembly of 43 human Y chromosomes reveals extensive complexity and variation” (Hallast et al., Nature). Taken together, these two papers provide intriguing insights into human Y chromosomes, reveal the highly variable nature of Y chromosomes across individuals, and provide an important foundation for future studies on how they may be contributing to certain disorders and diseases.

The need for long reads

Standard short-read genomic sequencing technologies require breaking genomic DNA into short (~250-base-long) fragments. These fragments are then reassembled into the full genome of more than 3 billion base pairs across 46 chromosomes in humans. The method is very accurate and works well for most, but not all, of the genome. Almost all “complete” human genome sequences, including the current reference genome sequence (known as GRCh38), are actually only about 90% complete, because it is difficult to assemble the highly repetitive and other complex sections accurately. GRCh38 falls particularly short for the Y chromosome, as it barely assembles half of that chromosome.

As a result, while the much larger and gene-rich other sex chromosome — the X chromosome — has been extensively studied, the Y chromosome has been often overlooked outside of male-based fertility studies. In a significant step forward for the genomics field, scientists from JAX, including first author and JAX Associate Research Scientist, Pille Hallast, Ph.D., with collaborators from Clemson University, Heinrich Heine University (Germany) and more, have now revealed a full picture of the Y chromosome’s key characteristics and differences between individuals for the first time. Of note is the striking variation in size and structure across the 43 Y chromosomes sequenced that covered 180,000 years of human evolution and range from 45.2 million to 84.9 million base pairs in length.

The inclusion of 43 different individuals representing diverse Y lineages allowed the researchers to redefine inter-chromosomal region boundaries and identify large-scale variations at an unprecedented resolution and clarity. The study also revealed an unexpected degree of structural variation across the Y chromosomes. For example, half of the euchromatin (gene-rich region) of the sequenced chromosomes carries large recurrent inversions — segments that contain the same nucleotide sequences but oriented in the opposite direction — at a rate much higher than anywhere else in the genome. The study further identified regions of the Y chromosome that demonstrate little single nucleotide variation but show high gene copy number variation for specific gene families. Other gene families tended to maintain their copy numbers, however, consistent with their roles in fertility and normal development.

Incredibly important research for overall health

“Having fully resolved Y chromosome sequences from multiple individuals is essential in order for us to begin to understand how this variation can affect function” says Hallast. “The degree of structural variation between individuals came as a big surprise to me, even though the nucleotide sequences within the Y chromosome genes are comparatively conserved. The variable gene copy numbers in certain gene families and extremely high inversion rates are almost certain to hold significant biological and evolutionary roles.”

The Y chromosome’s contributions to male health are poorly understood. Some unexpected indications of its importance to human health have recently come into focus in two new research studies that collectively implicate the Y chromosome in aggressive features of colorectal and bladder cancers in men. Indeed, one of the studies showed that tumors that had lost the Y chromosomes can more effectively evade T cell immunity, are infiltrated with higher numbers of dysfunctional CD8+ T cells, and are more responsive to anti-PD1 treatments compared to similar tumors retaining the Y chromosome.

“Research is emerging that shows proper Y chromosome gene function is incredibly important for the overall health of men,” says Lee, senior author on the paper. “Our study enables the inclusion of the full Y chromosome in all future studies when sequencing male genomes to understand health and disease.”