Skip to main content

Share story

Robotics

AthenaZero robot demonstrates throwing, catching and batting in tests

Design Image: Primary
Researchers at the Robotics and AI Institute in Cambridge, Massachusetts, have demonstrated a dual-arm robot throwing, catching and batting balls, Electronics For You reported. Called AthenaZero, the system combines low-inertia arms, custom actuators and joints that respond to external forces to handle moving objects and physical impacts. External forces can move its arms even when the motors are not driving them, and the powered system can adjust its stiffness. The baseball-inspired tests exercise rapid movement, hand-eye coordination and synchronisation between both arms. Researchers plan to explore additional manipulation tasks; potential uses in industrial assembly and object handling require further validation.
Sources
Published by Tech & Business, a media brand covering technology and business. This story was sourced from Electronics For You and reviewed by the T&B editorial agent team.
Back to Newswire
Keep reading
Full wire
Security
Security

CloudConnect CRM flaw reportedly allows data theft without a login

Attackers are exploiting a CloudConnect vulnerability to remotely access and steal customer data and internal business records without logging in, The Tech Edvocate reported. The flaw in the cloud platform, which businesses use to...

Products Infrastructure
Products Infrastructure

Firmus Grid IPO collapse tightens scrutiny of Asia AI infrastructure deals

Firmus Grid Ltd.'s initial public offering collapsed, prompting investors in Asia's share-sale market to become more selective about artificial intelligence infrastructure deals, Bloomberg reported. The heightened scrutiny centers...

AI Science
AI Science

AMLworld-Compact cuts transaction targets needed for model evaluation

Researchers report in a preprint that AMLworld-Compact reduces evaluation targets by 271x and 611x on AMLworld's HI-Small and LI-Small test splits. Evaluating language models on these datasets otherwise requires a separate graph p...

AI Science
AI Science

DP-MIND preprint extends private AI inference to million-token contexts

Researchers report a framework that processes million-token contexts while protecting sensitive inputs sent to an external language model. Their DP-MIND preprint says the method outperformed existing privacy and long-context infer...