Posts

Iván Hernández Dalas: Sven Koenig wins the 2026 ACM/SIGAI Autonomous Agents Research Award

Image
Congratulations to Sven Koenig on winning the 2026 ACM/SIGAI Autonomous Agents Research Award . This prestigious award is made for excellence in research in the area of autonomous agents. It is intended to recognize researchers in autonomous agents whose current work is an important influence on the field. Professor Sven Koenig was recognised “for his work on AI planning and search, which has shaped how intelligent agents reason and act in complex, dynamic environments. His contributions seamlessly bridge theory and practice, with a profound impact not only on AI and multi-agent systems, but also on robotics, where his algorithms have enabled robust, scalable autonomy in real-world robotic platforms” . Sven Koenig is Chancellor’s Professor and Bren Chair at the Computer Science Department of UC Irvine. A Fellow of AAAI, AAAS, and ACM, Professor Koenig has received several best paper awards from AAAI, ICALP and SoCS, and contributed to the community in numerous service roles, most r...
Read more

Iván Hernández Dalas: Lidar maker Ouster adds cameras with StereoLabs acquisition

Image
An aerial drone equipped with a Ouster lidar sensor. | Credit: Ouster Lidar maker Ouster is acquiring StereoLabs for $35 million and 1.8 million shares. StereoLabs makes vision-based perception systems for robots and industrial applications. Ouster said the deal enables it to offer a unified sensing and perception platform that combines lidar, cameras, AI compute, sensor fusion and perception software. StereoLabs, founded in 2010, said it has shipped more than 90,000 ZED cameras to over 10,000 customers, and will operate as a wholly owned subsidiary with its founding team continuing to lead the business. Ouster develops the OS Series and DF Series lidar sensors for 3D perception. By integrating the product lines, Ouster said it aims to simplify development for robotics platforms that must sense, think and act reliably in complex environments. “This acquisition builds on Ouster’s momentum and positions us as the foundational end-to-end sensing and perception platform for physi...
Read more

Iván Hernández Dalas: Destro AI launches Agentic AI Brain for human-robot collaboration

Image
Screenshot of Destro AI’s MothershipOS cloud-based orchestration engine. | Credit: Destro AI LAS VEGAS — Destro AI today emerged from stealth and launched its Agentic AI Brain, a centralized intelligence layer designed to coordinate robots and humans as a single adaptive system. The announcement coincided with the company’s public debut at Manifest, where it is showing live deployments of its technology in production environments. As robots become more capable, most deployments still rely on siloed intelligence — robots make local decisions, while humans and legacy systems handle planning, prioritization, and exception management, said Destro. This split limits scalability and forces operations teams to manually coordinate what should be autonomous behavior. “Robots today are smart locally, but dumb collectively,” said Manthan Pawar, founder and CEO of Destro AI. “We’re building the brain that lets robot agents and humans operate as one system — deciding, adapting, and executing t...
Read more

Iván Hernández Dalas: 11 reasons robots struggle to scale in high-mix manufacturing

Image
High-mix manufacturing poses many challenges for robotic automation. We have seen many impressive demonstrations of robotic automation in high-mix applications over the last 10 years. Often these demonstrations are at technology readiness level (TRL) 5 or 6 level. These demonstrations generate a great deal of interest in technology and people start expecting rapid technology transition. However, technology maturation in this area has been very slow. Very few robotics technologies have been actually deployed in high-mix applications. This article explores the reasons behind this slow transition. Robotic automation for high-mix applications requires a fundamentally different approach. Components of this approach include: 1. Sensor-based systems for building part and workspace models 2. Automated robot trajectory generation based on part models constructed from sensing 3. Control system to handle sensor uncertainties Most technology demonstration projects focus on development of ...
Read more

Iván Hernández Dalas: Flipping the script: How ‘upside-down’ AutoPallet robots solve palletizing density

Image
The AutoPallet system uses magnets to drive on steel panels mounted overhead and to pick and place cases on pallets and conveyors below. | Credit: AutoPallet AutoPallet Robotics is focused on solving palletizing challenges with a novel warehouse robot. The startup made the first public demonstration of its palletizing/depalletizing system at Manifest 2026 today. Its founders got their start at Y Combinator in 2024. The AutoPallet robots are small autonomous mobile robots ( AMRs) that drive upside down, magnetically affixed to a steel plate positioned over the target workspace. The robots lower a vacuum gripper down to a pallet or conveyor to acquire a box, then lift the box up and carry it to the target drop location. The freestanding modular superstructure bolts into the warehouse floor, allowing operators to drop high-density automation into existing buildings without redesigning their entire material flow. “We started from the question, ‘What would a purpose-built, modern ro...
Read more

Iván Hernández Dalas: What the SpaceX acquisition of xAI means for industrial robotics

Image
Aerospace manufacturing could lead the way to integrating automation and AI, says Flexxbotics. Source: Flexxbotics The news that SpaceX is bringing xAI into its core operations isn’t just another big tech acquisition. In his announcement, Elon Musk made the near-term implications surprisingly concrete for anyone working in automation and robotics. It described the massive scale of rocket and satellite production as a “forcing function” similar to how SpaceX’s launch demands have driven rapid improvements in engineering and flight operations. In practical terms, that means AI isn’t being adopted as an experiment or side project. It’s being pulled directly into the heart of the company ‘s automated production because the volume, speed, and complexity of manufacturing now require it. When output must scale by orders of magnitude, manual optimization, disconnected data systems, and slow process learning simply can’t keep up. AI becomes necessary to: Understand complex production ...
Read more

Iván Hernández Dalas: KinetIQ framework from Humanoid orchestrates robot fleets

Image
KinetIQ is a single AI model that can control different morphologies and end-effector designs. | Source: Humanoid Humanoid, a developer of humanoid robots and mobile manipulators, this week introduced KinetIQ. This is the London-based company’s own AI framework for orchestration of robot fleets across industrial, service, and home applications. With KinetIQ, a single system controls robots with different embodiments and coordinates interactions between them, said SKL Robotics Ltd., which does business as Humanoid. The architecture is cross-timescale: Four layers operate simultaneously, from  fleet -level goal assignment to millisecond-level joint control. Each layer treats the layer below as a set of tools, orchestrating them via prompting and tool use to achieve goals set from above. This agentic pattern, proven in frontier  AI  systems, allows components to improve independently while the overall system scales naturally to larger fleets and more complex tasks. Hum...
Read more