Lifeboat Foundation: Safeguarding Humanity
Toggle light / dark theme

Blog

Category: robotics/AI – Page 840

The fascinating collective behaviors of biological systems have inspired extensive studies on shape assembly of robot swarms6,7,8,9. One class of strategies widely studied in the literature are based on goal assignment in either centralized or distributed ways10,11,12. Once a swarm of robots are assigned unique goal locations in a desired shape, the consequent task is simply to plan collision-free trajectories for the robots to reach their goal locations10 or conduct distributed formation control based on locally sensed information6,13,14. It is notable that centralized goal assignment is inefficient to support large-scale swarms since the computational complexity increases rapidly as the number of robots increases15,16. Moreover, when robots fail to function normally, additional algorithms for fault-tolerant detection and goal re-assignment are required to handle such situations17. As a comparison, distributed goal assignment can support large-scale swarms by decomposing the centralized assignment into multiple local ones11,12. It also exhibits better robustness to robot faults. However, since distributed goal assignments are based on locally sensed information, conflicts among local assignments are inevitable and must be resolved by sophisticated algorithms such as local task swapping11,12.

Another class of strategies for shape assembly that have also attracted extensive research attention are free of goal assignment18,19,20,21. For instance, the method proposed in ref. 18 can assemble complex shapes using thousands of homogeneous robots. An interesting feature of this method is that it does not rely on external global positioning systems. Instead, it establishes a local positioning system based on a small number of pre-localized seed robots. As a consequence of the local positioning system, the proposed edge-following control method requires that only the robots on the edge of a swarm can move while those inside must stay stationary. The method in ref. 19 can generate swarm shapes spontaneously from a reaction-diffusion network similar to embryogenesis in nature. However, this method is not able to generate user-specified shapes precisely. The method in ref. 21 can aggregate robots on the frontier of shapes based on saliency detection. The user-defined shape is specified by a digital light projector. An interesting feature of this method is that it does not require centralized edge detectors. Instead, edge detection is realized in a distributed manner by fusing the beliefs of a robot with its neighbors. However, since the robots cannot self-localize themselves relative to the desired shape, they make use of random walks to search for the edges, which would lead to random trajectories. Another class of methods that do not require goal assignment is based on artificial potential fields22,23,24,25. One limitation of this class of methods is that robots may easily get trapped in local minima, making it difficult to assemble nonconvex complex shapes.

Here, we propose a strategy for shape assembly of robot swarms based on the idea of mean-shift exploration: when a robot is surrounded by neighboring robots and unoccupied locations, it would actively give up its current location by exploring the highest density of nearby unoccupied locations in the desired shape. This idea does not rely on goal assignment. It is realized by adapting the mean-shift algorithm26,27,28, which is an optimization technique widely used in machine learning for locating the maxima of a density function. Moreover, a distributed negotiation mechanism is designed to allow robots to negotiate the final desired shape with their neighbors in a distributed manner. This negotiation mechanism enables the swarm to maneuver while maintaining a desired shape based on a small number of informed robots. The proposed strategy empowers robot swarms to assemble nonconvex complex shapes with strong adaptability and high efficiency, as verified by numerical simulation results and real-world experiments with swarms of 50 ground robots. The strategy can be adapted to generate interesting behaviors including shape regeneration, cooperative cargo transportation, and complex environment exploration.

Read more | >

Researchers claim the new electronic chip can mimic human vision and memory, which could help make self-driving cars smarter.

Researchers at the Royal Melbourne Institute of Technology (RMIT) have successfully developed a tiny electronic device that, they claim, can mimic human vision and memory. This could be a promising step to one-day developing sophisticated ways to make rapid decision-making in self-driving cars.

A team of engineers from RMIT University in Australia, along with researchers from Deakin University and the University of Melbourne, developed the device using a sensing element called doped indium oxide, which is thousands of times thinner than a strand of human hair and… More.

Continue reading “Innovative human eye-mimicking chip has been developed at RMIT” | >

MusicGen has been trained on 20,000 hours of music.

Meta has unveiled MusicGen, an artificial intelligence(AI) music-generating system which can be conditioned using text prompts or melodies. It’s similar to Google’s MusicLM, which can build on existing melodies, whether they are whistled, hummed, sung, or played on an instrument.

Generating music is a challenging task as it contains harmonies and melodies from different instruments, which create complex structures. Meta’s model was trained on 20,000 hours of music, reported Tech Xplore. Meta released a demo of MusicGen on Hugging Face, and Interesting Engineering decided to have a go at it.

Read more | >

Amazon’s cloud computing unit likes to build its services from the ground up, and AMD could be the perfect fit.

When Advanced Micro Devices (AMD) unveiled its new artificial intelligence (AI) chip during a keynote presentation in San Francisco on Tuesday, Wall Street reacted by sending its stock price down by 3.5 percent. This was attributed to the lack of a prospective buyer for the chip. It has now emerged that Amazon is considering the chip for its cloud unit, as per a Reuters.

AI models are the new buzzword in the tech industry, and Nvidia has hogged all the limelight when it comes to powering them. Once known for making great graphic cards for gaming purposes, Nvidia has recently gained popularity for its chips powering great AI models.

Read more | >

A first-of-its-kind robot which gives clinicians the ability to ‘feel’ patients remotely has been launched as part of a Finnish hospital pilot by deep tech robotics company Touchlab, a new tenant of the world-leading centre for robotics and artificial intelligence the National Robotarium.

Controlled by operators wearing an electronic haptic glove, the Välkky telerobot is equipped with the most advanced electronic skin (e-skin) technology ever developed to transfer a sense of touch from its robotic hand to users. E-skin is a material which is made up of single or multiple ultra-thin force sensors to transmit tactile sensations like pressure, vibration or motion from one source to another in real-time.

The 3-month pilot at Laakso Hospital in Helsinki, Finland will see a team of purpose-trained nurses explore how robotics systems can help deliver care, reduce workload and prevent the spread of infections or diseases. The pilot at Laakso Hospital is coordinated by Forum Virium Helsinki, an innovation company for the City of Helsinki. The research is part of a wider €7 billion project aimed at developing the most advanced hospital in Europe, due to be completed in 2028.

Read more | >

Alongside their EPYC server CPU updates, as part of today’s AMD Data Center event, the company is also offering an update on the status of their nearly-finished AMD Instinct MI300 accelerator family. The company’s next-generation HPC-class processors, which use both Zen 4 CPU cores and CDNA 3 GPU cores on a single package, have now become a multi-SKU family of XPUs.

Joining the previously announced 128GB MI300 APU, which is now being called the MI300A, AMD is also producing a pure GPU part using the same design. This chip, dubbed the MI300X, uses just CDNA 3 GPU tiles rather than a mix of CPU and GPU tiles in the MI300A, making it a pure, high-performance GPU that gets paired with 192GB of HBM3 memory. Aimed squarely at the large language model market, the MI300X is designed for customers who need all the memory capacity they can get to run the largest of models.

First announced back in June of last year, and detailed in greater depth back at CES 2023, the AMD Instinct MI300 is AMD’s big play into the AI and HPC market. The unique, server-grade APU packs both Zen 4 CPU cores and CDNA 3 GPU cores on to a single, chiplet-based chip. None of AMD’s competitors have (or will have) a combined CPU+GPU product like the MI300 series this year, so it gives AMD an interesting solution with a truly united memory architecture, and plenty of bandwidth between the CPU and GPU tiles.

Read more | >

Meta-formerly-Facebook CEO Mark Zuckerberg has a genius new plot to add some interest to Meta-owned products: just jam in some generative AI, absolutely everywhere.

Axios reports that in an all-hands meeting on Thursday, Zuckerberg unveiled a barrage of generative AI tools and integrations, which are to be baked into both Meta’s internal and consumer-facing products, Facebook and Instagram included.

“In the last year, we’ve seen some really incredible breakthroughs — qualitative breakthroughs — on generative AI,” Zuckerberg told Axios in a statement, “and that gives us the opportunity to now go take that technology, push it forward, and build it into every single one of our products.”

Read more | >

The remarkable zero-shot learning capabilities demonstrated by large foundation models (LFMs) like ChatGPT and GPT-4 have sparked a question: Can these models autonomously supervise their behavior or other models with minimal human intervention? To explore this, a team of Microsoft researchers introduces Orca, a 13-billion parameter model that learns complex explanation traces and step-by-step thought processes from GPT-4. This innovative approach significantly improves the performance of existing state-of-the-art instruction-tuned models, addressing challenges related to task diversity, query complexity, and data scaling.

The researchers acknowledge that the query and response pairs from GPT-4 can provide valuable guidance for student models. Therefore, they enhance these pairs by adding detailed responses that offer a better understanding of the reasoning process employed by the teachers when generating their responses. By incorporating these explanation traces, Orca equips student models with improved reasoning and comprehension skills, effectively bridging the gap between teachers and students.

The research team utilizes the Flan 2022 Collection to enhance Orca’s learning process further. The team samples tasks from this extensive collection to ensure a diverse mix of challenges. These tasks are then sub-sampled to generate complex prompts, which serve as queries for LFMs. This approach creates a diverse and rich training set that facilitates robust learning for the Orca, enabling it to tackle a wide range of tasks effectively.

Read more | >