A novel technique is aiding robots in efficiently packing objects into tight spaces. MIT researchers harnessed a family of generative AI models to collaboratively tackle complex robot manipulation challenges that require multiple steps.

Packing a substantial amount of luggage into a car’s trunk, much like trying to solve dense packing problems, poses a significant challenge. Robots, too, grapple with such tasks.

For robots, solving the packing problem entails meeting various constraints, such as stacking luggage to prevent it from spilling, ensuring heavier items aren’t atop lighter ones, and preventing collisions between the robot arm and the car’s bumper.

Conventional methods address this issue step by step, guessing partial solutions that meet one constraint at a time and subsequently checking for violations of other constraints. With an extensive sequence of actions and a pile of luggage to handle, this process becomes impractically time-consuming.

To address this, MIT researchers employed a form of generative AI known as a diffusion model. Their approach employs a set of machine-learning models, each specializing in representing a specific constraint. These models combine forces to generate global solutions to the packing problem, factoring in all constraints simultaneously.

Their approach proved capable of generating effective solutions faster than other techniques and producing a greater number of successful solutions within the same timeframe. Importantly, it could handle problems with novel combinations of constraints and larger sets of objects, which the models hadn’t encountered during training.

Thanks to its adaptability, this technique can teach robots to grasp and adhere to overall constraints in packing problems, including the importance of collision avoidance or the desire for specific objects to be adjacent to each other. Robots trained in this manner can be applied to a wide range of complex tasks in various settings, from warehouse order fulfillment to home bookshelf organization.

Zhutian Yang, a graduate student in electrical engineering and computer science at MIT and the lead author of a paper on this new machine-learning technique envisions pushing robots to tackle more intricate tasks characterized by numerous geometric constraints and continuous decision-making, typical of service robots operating in diverse human environments. She believes that compositional diffusion models can empower robots to address these complex problems and achieve remarkable generalization results.

The research was a collaborative effort involving MIT graduate students Jiayuan Mao and Yilun Du, Jiajun Wu, an assistant professor of computer science at Stanford University, Joshua B. Tenenbaum, a professor in MIT’s Department of Brain and Cognitive Sciences and a member of the Computer Science and Artificial Intelligence Laboratory (CSAIL), Tomás Lozano-Pérez, an MIT professor of computer science and engineering and a member of CSAIL, and senior author Leslie Kaelbling, the Panasonic Professor of Computer Science and Engineering at MIT and a member of CSAIL. The findings will be presented at the Conference on Robot Learning.

While still in the early stages, this approach holds promise for enabling more efficient, safe, and reliable autonomous systems in various applications.

In a groundbreaking move to bolster safety measures at the UK’s largest renewable power station, Drax has introduced a cutting-edge robotic dog named “Sparky.” This innovative creation is equipped with a camera, enabling it to conduct comprehensive safety checks and identify potential hazards at the Drax facility located near Selby in North Yorkshire.

Drax emphasized that Sparky’s deployment would facilitate the collection of superior information while ensuring the safety of its workforce by keeping them out of harm’s way. This remarkable robotic canine belongs to the renowned “Spot” lineage of robodogs, manufactured by the US-based company Boston Dynamics.

This bright-yellow robotic marvel will also be programmed to navigate tailored routes throughout the facility, granting it the capability to operate autonomously. Richard Barber, the maintenance systems lead engineer at Drax, expressed his enthusiasm, describing Sparky’s integration as a true “game-changer” for their operations.

He elaborated, stating, “The technology empowers our team to gather more accurate information regarding our equipment while concurrently safeguarding our colleagues from potential risks.” Barber further highlighted Sparky’s camera, which allows for close examination of equipment, and its thermal infrared camera, which can detect hotspots or thermal irregularities in machinery.

“Our goal is to prevent faults from occurring rather than simply addressing them once they arise,” he emphasized. “With Sparky patrolling the power station, we will be well-equipped to achieve this objective.”

Notably, robotic dogs have already been deployed for various tasks across the UK, including conducting surveys at two Cold War weapons testing facilities. Moreover, in Singapore, this technology was utilized during the pandemic to enforce social distancing measures.

In the heart of Manhattan’s Times Square, the NYPD has welcomed its newest team member, a robust and tireless robot weighing in at 400 pounds. This dedicated member works through the midnight hours, drawing no complaints and earning a modest wage of $9 an hour, much to the satisfaction of transit commanders.

Meet K5, a vigilant robot entrusted with patrolling the Times Square subway station during the overnight shift. Outfitted with an array of cameras and two-way communication capabilities, K5’s primary mission is to deter criminal activities and capture any unlawful incidents as they unfold.

What’s more, it comes equipped with a panic button that allows subway riders to swiftly alert patrol officers if the need arises. NYPD Transit Division Chief Michael Kemper expressed, “We are enhancing the subway system’s existing costly camera network by introducing K5, a mobile device that not only augments it but also connects subway passengers to immediate assistance when necessary.”

With the daily subway ridership surpassing four million—the highest since the pandemic began—crime underground has been on the decline. However, violent assaults remain over 50% higher than they were four years ago. In response to the evolving landscape, the NYPD is embracing a range of robotic technologies, including dogs, drones, tracking devices, and now, robots like K5.

Leased from its manufacturer, Knightscope, K5 boasts facial recognition capabilities and listening devices, though Mayor Eric Adams has assured the public that neither feature will be activated.

He emphasized, “While it is our responsibility to leverage cutting-edge technological advancements for the safety of New Yorkers, we must do so prudently and without invading privacy.” For the initial two months of the pilot program, K5 will be accompanied by a uniformed police officer, primarily to address inquiries from curious commuters. Following this phase, a solo deployment is scheduled, just in time for the bustling holiday tourist season.

The MSG Sphere, already Earth’s largest sphere with massive LED screens inside and out, is now set to usher Las Vegas into the future with the introduction of robots. Sphere Entertainment proudly presents Aura, an advanced humanoid robot that will permanently reside at the arena, debuting this month.

Located within the grand atrium of the venue, five Aura robots will warmly greet arriving guests and provide informative responses to their inquiries, as announced by MSG Ventures CEO David Dibble. These “spokesbots” are engineered to maintain lifelike facial expressions and exhibit fluid mobility, creating a captivating spectacle.

Capitalizing on the vast space of the atrium, large enough to accommodate the Statue of Liberty or the Saturn V rocket, MSG Entertainment Chairman James L. Dolan sought to convey the significance of technology and science in the evolution and pursuit of humanity. Dibble expressed his admiration for Aura’s facial movements and recognition, acknowledging that some might find it eerie, yet everyone will find it utterly fascinating. He explained how Aura follows, tracks, and interacts with individuals as they move about.

In a departure from traditional carnival fortune teller robots, Aura possesses voice recognition capabilities and can focus on one person speaking directly in front of her, even in a group setting, according to Dibble.

Dibble added that Aura will harness artificial intelligence to enhance her understanding of humans through guest interactions, but the company plans to proceed cautiously with AI development to monitor its evolution. Human lab technicians will accompany the robots, sharing the story of humanity’s history of innovation, including the Sphere, to enrich the Sphere Experience for visitors.

Aura’s role extends to providing lost guests with directions within the venue, delivering details about daily performances, and answering questions about the Sphere’s engineering, technology, and creative mission. Additionally, the robot will serve as the Sphere’s brand ambassador, overseeing digital platforms and social channels.

In a press release, Aura offered a friendly greeting: “Hello, humans. While I understand the most complex concepts of math and science — you remain a mystery. Your emotions, your humor, and your relationship with technology require further study, so you must visit me at Sphere. I am excited to meet you and introduce you to the future of live entertainment at my new home.”

Each physical embodiment of a humanoid, created in early 2022, required three to four months to produce, according to the company.

Sphere Entertainment had previously teased Aura on their social media platforms and during a commercial that aired during the Academy Awards in March.

MSG Sphere will officially open to the public on September 29, commencing with a series of 25 concerts featuring U2. “U2: UV Achtung Baby Live at Sphere” will run until mid-December, celebrating the Irish band’s 1991 album “Achtung Baby.”

Bono of U2 noted, “Most music venues are sports venues. They’re built for sports – they’re not built for music. They’re not built for art. This building was built for immersive experiences in cinema and performance.”

On October 6, The MSG Sphere will premiere a 360-degree experience titled “Postcard From Earth,” written and directed by Darren Aronofsky. This show will mark the debut of the first Sphere Experience. Aronofsky recently shared an exclusive first-look video from inside the Sphere on his Instagram page, providing a breathtaking preview of the 160,000-square-foot display plane designed for immersive experiences.

A new Canadian grid analytics company based in Waterloo aims to predict power outages using robotics. Chief Technology Officer Anson Maitland told CTV News, “We’re pioneering a new approach that hasn’t been tried before. By using a device like this, we’re reducing the need for workers in hazardous environments.”

As reported by CTV News, Enerza, the world’s first provider of a conditional risk assessment tool to electrical utility providers through autonomous on-wire robotic monitoring, is leading the charge. Enerza’s robotic technology aims to enhance the safety and reliability of power grids, making working conditions on the lines safer and more efficient.

Switching from manual inspections to robotic ones enhances safety by eliminating human error and automating processes. Currently, inspections are primarily done manually, with workers visually inspecting power lines, often in remote areas using ATV trucks. Enerza’s solution incorporates advanced technology to replace human tasks. The robot can fly to the power lines using propellers, utilizing thermal cameras, depth cameras, and stereoscopic cameras to measure distances.

This innovative robot not only detects failing infrastructure but also anticipates future grid issues, such as overgrown branches near electrical lines, preventing potential problems. Moreover, Enerza’s approach is cost-effective and highly efficient. It allows utilities to cover the entire grid, reducing costs by up to 1,220 times and increasing efficiency by at least 200 percent.

Real-time access to grid data through Enerza’s Insight Dashboard further enhances its effectiveness. Enerza’s mission is to achieve a sustainable future with fewer power outages. Grid reliability and resiliency are critical concerns for utilities and the public. Their proactive approach to grid health aims to benefit everyone.

While Enerza is pioneering this technology, it’s worth noting that similar innovations are occurring globally. In 2022, China’s state-owned power grid company introduced an AI system that rapidly resolved power issues, reducing intervention time from hours to seconds.

Multiple sensors with autonomous decision-making capabilities streamlined grid activities, eliminating the need for human intervention. These advancements in power grid technologies contribute to ongoing energy efficiency, ensuring a safer and more comfortable life for all.