Can AI Truly Navigate Like Humans?
A new benchmark assesses the ability of advanced AI models to perform goal-oriented navigation in complex urban environments, revealing critical limitations in spatial understanding.
Science
Smarter Growing: AI-Powered Climate Control for Modern Farms
A new IoT platform, IOGRUCloud, is delivering significant energy savings and improved automation across dozens of commercial controlled environment agriculture facilities.
Robots Learn to Grasp by Watching Dreams
Researchers have developed a new method allowing robots to learn functional grasping skills by imitating demonstrations generated from AI-powered video simulations.
When AI Players Clash: Ensuring Stability in Multi-Agent Systems
New research details how to maintain predictable behavior when multiple AI agents, each with potentially differing goals, compete within a complex control system.
Seeing is Believing: An Open Foundation for Web Agents
Researchers have unveiled MolmoWeb, a new open-source toolkit and dataset designed to empower the development of web agents capable of sophisticated visual web browsing.
Robots Learn to Walk and Work
A new control framework empowers robots to seamlessly combine locomotion and manipulation tasks, opening doors for more versatile and adaptable robotic systems.
Thinking Through Movement: A Smarter Approach to Robot Navigation
![HiRO-Nav achieves superior navigational performance, exceeding the capabilities of the Poliformer method, even when guided by action state machine (ASM) estimations derived from deep models-demonstrated through repeated evaluations and evidenced by pass@k curves that indicate its ability to successfully complete tasks with a high degree of accuracy, despite the inherent noise in deep model estimations of [latex]ASM[/latex].](https://arxiv.org/html/2604.08232v1/x11.png)
Researchers have developed a new agent that balances skillful navigation with efficient reasoning, paving the way for more adaptable and intelligent robots.
Learning Goals From Motion: A New Approach to Reward Machine Inference
Researchers have developed a novel framework for automatically discovering reward functions from observed behavior, bypassing the need for manual labeling.
Robots That See Less: Balancing Privacy and Navigation
New research demonstrates a dynamic approach to robot vision, adjusting image resolution based on proximity to sensitive areas to better respect user privacy.
Robots Judge Animal Behavior Models in the Real World
![A framework assesses the fidelity of simulated fish behavior to reality by training behavioral models on live fish trajectories, utilizing these models to train reinforcement learning control policies in simulation, and then quantifying discrepancies between simulated and real fish-robot interactions to estimate model realism-a process fundamentally grounded in closing the loop between [latex] \text{simulation} [/latex] and [latex] \text{reality} [/latex].](https://arxiv.org/html/2604.07303v1/visual_abstract.png)
New research uses biomimetic robots and reinforcement learning to rigorously test and compare computational models of collective animal behavior, moving beyond simulation.