Articles tagged with "multi-agent-systems"
Generations in Dialogue: Multi-agent systems and human-AI interaction with Professor Manuela Veloso - Robohub
The article introduces "Generations in Dialogue: Bridging Perspectives in AI," a new podcast series by the Association for the Advancement of Artificial Intelligence (AAAI) that features conversations between AI experts from diverse generations and backgrounds. The podcast explores how different generational experiences influence perspectives on AI, addressing challenges, opportunities, and ethical considerations in the development of AI technologies. The inaugural episode features Professor Manuela Veloso, a leading figure in AI research, discussing her career journey, the evolution of AI, inter-generational collaboration, and the role of AI in assisting humans, particularly in finance. Professor Manuela Veloso is highlighted as a pioneer in multi-agent systems, robotics, and human-AI collaboration. Currently, she leads AI research at JPMorgan Chase, focusing on integrating AI into financial services. Her distinguished academic career includes positions at Carnegie Mellon University and numerous accolades from major AI organizations such as AAAI, IEEE, and AAAS. The podcast host, Ella Lan, is a Stanford University student and
robotartificial-intelligencemulti-agent-systemshuman-AI-interactionroboticsautonomous-systemsAI-ethicsNew algorithm lets drones transport heavy objects together in remote areas
Researchers at TU Delft have developed a novel algorithm enabling multiple drones to collaboratively lift, transport, and precisely control the orientation of heavy payloads via cables. This system addresses the limitations of single drones, which have restricted load capacities, by coordinating several drones to carry heavier objects and adapt in real time to changing payload dynamics and external disturbances such as wind or sudden movements. Unlike traditional control methods that are slow and rigid, this new algorithm offers fast, flexible, and robust control without needing sensors on the payload itself, significantly enhancing operational agility. The algorithm employs a trajectory-based framework that solves the kinodynamic motion planning problem online, accounting for the dynamic coupling between drones and the load. Real-world lab experiments demonstrated that the system achieves at least eight times greater acceleration than existing methods, enabling agile maneuvers even with complex payloads. Currently tested indoors using motion capture cameras, the team aims to adapt the technology for outdoor use, targeting applications in remote construction, agriculture, and search and rescue. The autonomous drones require
roboticsdronesmulti-agent-systemspayload-transportcontrol-algorithmsautonomous-flightdrone-coordinationVERSES multi-agent robotics model works without pre-training - The Robot Report
VERSES AI Inc. has developed a novel multi-agent robotics architecture based on hierarchical active inference that enables robots to perform typical household tasks more effectively than existing models without requiring any pre-training. Unlike traditional robotics approaches—drive-by-wire systems that rely on pre-programming and deep learning models that need extensive training data—VERSES’ system adapts dynamically by exploring its environment, using integrated vision, planning, and control modules. This approach allows robots to handle unexpected obstacles and changes in their surroundings, overcoming common limitations such as freezing or halting when encountering unfamiliar situations. The company, founded in 2020 and based in Vancouver, emphasizes that its platform is inspired by principles from science, physics, and biology to generate reliable predictions and decisions under uncertainty. In comparative tests involving household tasks like tidying a room, preparing groceries, and setting a table, the VERSES model achieved a 66.5% success rate, outperforming a deep learning baseline that scored 54.7%. VERSES claims this
roboticsartificial-intelligencemulti-agent-systemsadaptive-robotsautomationVERSES-AIrobotics-architectureTiny but mighty: This AI mini-model outsmarted Microsoft on Meta’s GAIA benchmark
Coral Protocol, a London-based AI company, has achieved a significant milestone by developing a multi-agent AI "mini-model" system that outperformed Microsoft’s agent platform by approximately 34% on Meta’s GAIA benchmark. GAIA is a challenging test suite comprising nearly 450 complex real-world tasks requiring reasoning, web browsing, data analysis, and tool use. While human participants typically answer about 92% of GAIA questions correctly, advanced large models like GPT-4 manage only around 15%. Coral’s mini-model scored the highest among small-scale AI systems, surpassing Microsoft-backed Magnetic-UI, which scored about 30%. Coral’s approach diverges from the traditional AI scaling method of building massive models with billions of parameters. Instead, it employs horizontal scaling by orchestrating many specialized, lightweight mini-models that collaborate in real time, each excelling at specific tasks such as natural language understanding or coding. This collective intelligence framework enables faster, more cost-effective, and potentially more secure
IoTartificial-intelligenceAI-assistantsmulti-agent-systemsAI-mini-modelshorizontal-scalingCoral-ProtocolShlomo Zilberstein wins the 2025 ACM/SIGAI Autonomous Agents Research Award
robotautonomous-agentsmulti-agent-systemsdecision-makingreinforcement-learningresearch-awardAIMulti-agent path finding in continuous environments
robotautonomous-drivingmulti-agent-systemspath-findingwarehouse-logisticscollision-avoidancerobotics