Category: Robotics

As e-commerce deliveries surge, maintaining affordable delivery costs remains a challenge. Vayu Robotics Inc., based in Palo Alto, California, addresses this issue with the release of a groundbreaking delivery robot. This robot integrates advanced artificial intelligence models with cost-effective sensors, promising to transform the delivery landscape.

Technological Breakthroughs and Vision

Anand Gopalan, CEO of Vayu Robotics, emphasized the uniqueness of their technology. “The unique set of technologies we have developed at Vayu have allowed us to solve problems that have plagued delivery robots over the past decade and finally create a solution that can actually be deployed at scale and enable the cheap transport of goods everywhere,” Gopalan stated. Vayu was co-founded by industry veterans Anand Gopalan, former CEO of Velodyne; Mahesh Krishnamurthi, who previously worked at Apple SPG and Lyft; and Nitish Srivastava, also from Apple SPG and Geoffrey Hinton’s AI lab at the University of Toronto. Geoffrey Hinton serves as an advisor to the company.

The first self-checkout system was installed in 1986 in a Kroger grocery store just outside of Atlanta. While it took several decades for the technology to proliferate across the U.S., grocery stores are now firmly headed in the direction of automation. With this trend, robotic bagging seems to be the next logical step. MIT’s CSAIL department is at the forefront of this development, showcasing their new system called RoboGrocery.

RoboGrocery combines computer vision with a soft robotic gripper to bag a wide range of grocery items. To test the system, researchers placed 10 unknown objects on a grocery conveyor belt. The products included delicate items such as grapes, bread, kale, muffins, and crackers, as well as sturdier items like soup cans, meal boxes, and ice cream containers.

A team of researchers at Bristol University has developed a highly dexterous four-fingered robotic hand with artificial tactile fingertips, named AnyRotate. This innovative robotic hand can sense and rotate objects in any direction and orientation, even when the hand is upside down—a capability never achieved before.

Achieving this level of dexterity required the extraction and utilization of rich touch information for precise motor control. The researchers believe that enhancing the dexterity of robotic hands could significantly advance automated tasks such as handling supermarket goods or sorting recycling waste. The details of their research are available on GitHub.

Researchers from Uppsala University and Karolinska Institutet in Sweden have developed a groundbreaking robotic hand that can sense touch like a human. This innovation promises significant advancements in tactile prosthetics and robotics.

The robotic hand was created through a collaboration between Uppsala University’s Signals and Systems Division and the Department of Neurobiology, Care Sciences and Society, Division of Neurogeriatrics at Karolinska Institutet. The team leveraged data processing and machine learning to develop the system.

A short video clip circulating on social media has sparked both amusement and concern, unveiling the inner workings of a Chinese humanoid robot factory. The video provides a fascinating glimpse into the rapid advancements in robotics technology, showcasing numerous humanoid robots at various stages of development.

Uploaded on TikTok from the manufacturing floor of Chinese robotics firm Ex Robots, the video highlights the company’s impressive progress. At the 2023 World Robot Conference, Ex Robots showcased an array of humanoid robots, surprising attendees with their hyper-realistic appearances and movements, which closely mimic human behavior.

In a remarkable stride forward for aviation, engineers at the Korea Advanced Institute of Science & Technology (KAIST) are at the forefront of developing a humanoid robot capable of piloting aircraft with unparalleled precision. Named PIBOT, this groundbreaking creation symbolizes the culmination of decades of advancements in artificial intelligence (AI) and robotics, marking a significant milestone in the quest for humanoid robot pilots.

The journey toward creating humanoid robot pilots has been propelled by extraordinary progress in AI technology. From rudimentary rule-based systems to sophisticated neural networks, AI has evolved to closely mimic human cognition. This evolution has empowered machines to learn from vast datasets, adapt to diverse scenarios, and execute complex tasks with remarkable accuracy, paving the way for innovations like PIBOT.

At the 2024 European Robotics Forum in Rimini, Italy, researchers from the Istituto Italiano di Tecnologia (IIT) presented the latest advancements from the SOPHIA project. These innovations include collaborative robots, wearable devices, and feedback mechanisms designed to alleviate the strain of overhead tasks, support heavy lifting, and alert users to ergonomic risks, ultimately preventing Musculoskeletal Disorders (MSDs) in industrial settings.

The SOPHIA project, initiated in 2020 and coordinated by Arash Ajoudani of IIT’s Human-Robot Interfaces and Interaction (HRI2) lab, aimed to develop next-generation collaborative robots and intelligent wearables to enhance worker ergonomics and manufacturing flexibility for mass customization. Over four years, the project engaged 12 partners from six European countries, resulting in groundbreaking technologies tailored for industrial environments.

At Modex in Atlanta this week, while Agility’s Digit garnered attention, Reflex Robotics, a burgeoning startup, was making waves on the other side of the Georgia World Congress Center. With a single demo captivating passersby, Reflex showcased its humanoid robot in action, efficiently retrieving items from shelves – a spectacle made even more enticing with free food and beverages on offer.

Impressive Speed and Accuracy The Reflex robot, with its in-house designed hardware, features a dynamic “torso” mounted to a base, allowing for agile movement of arms and sensors. This design ensures remarkable dexterity, enabling the robot to access shelves at various heights and navigate tight spaces with ease. Equipped with a wheeled base, the system effortlessly maneuvers through complex layouts. While primarily tele-operated, the robot showcases near-human efficiency, with Co-founder and CEO Ritesh Ragavender likening the interface to a video game.

Trailer unloading has long been a labor-intensive task, prompting the rise of robotics companies offering solutions. Among them, Anyware Robotics believes it has struck the right balance of safety, capability, and cost with its Pixmo robot. While the concept of a truck-unloading robot is not new, Pixmo stands out with its clever yet straightforward box-handling solution.

Pixmo’s design includes a mobile base with an arm that maneuvers into trailers, employing suction to lift stacked boxes onto a conveyor belt. What sets Pixmo apart is its integration of a heavy-payload collaborative arm from Fanuc, making it ISO-certified safe to work alongside humans. By utilizing off-the-shelf components and contracting out the base to a robotics OEM, Anyware Robotics streamlines the supply chain and ensures reliability.

Cotton, a staple crop in the U.S. with an annual harvest value of around US$7 billion, plays a crucial role in various industries. From clothing to medical supplies and home goods, cotton is ubiquitous. The traditional method of picking cotton manually, however, presents challenges that researchers at Martin Luther University Halle-Wittenberg (MLU) are addressing with innovative robotics and automation.

The team, led by an engineer with nearly two decades of research experience in agricultural machinery, is focused on developing a robotic cotton harvester that minimizes damage to both the product and the soil. Recognizing the economic, environmental, and agricultural benefits of a more efficient harvesting option, the researchers aim to overcome the limitations of large, heavy mechanical harvesters currently in use.

In the ever-evolving landscape of AI-powered restaurants, Remy Robotics, a Spanish foodservice robotics company, is making waves with its innovative approach. Unlike traditional robot-run establishments, Remy Robotics’ new venture, “Better Days,” in New York City, combines the precision of robots with human expertise for a unique dining experience.

A New Era in AI-Powered Dining

Better Days, described as a health-focused fast-fine restaurant, utilizes Remy Robotics’ platform to create a human-free storefront. The distinctive aspect of this model involves off-site preparation by human chefs, who then deliver the menu to the automated restaurant. Robot arms take over to complete the final stages of food preparation, blending the strengths of robots’ precision with human culinary skills.

In the realm of robotics, the integration of generative AI is heralding a transformative era, ushering in a synergy that promises unparalleled technological advancements. While conventional robots are essential for manufacturing and home applications, the emergence of generative AI is paving the way for a new generation of intelligent robots. As we navigate through the final quarter of 2023, experts predict that the fusion of these technologies will redefine the landscape of robotics.

Vaclav Vincalek, virtual CTO, and founder of 555vCTO.com emphasizes the inevitability of generative AI integration with robotics. He notes that major players like Boston Dynamics and Sanctuary AI are actively working towards developing robots that transcend traditional functionalities. These companies aspire to create robots capable of mastering diverse terrains while maintaining balance. According to Vincalek, the incorporation of generative AI for ‘robot vision’ is instrumental in achieving these goals. Advancements in object detection, image segmentation, and image generation will play a pivotal role in enhancing the capabilities of smart robots, addressing challenges such as designing robotic hands capable of both lifting heavy objects and delicately handling fragile items like eggs.