Topic
Robotics & Embodied AI
The latest AI xPress posts in Robotics & Embodied AI.
- Robotic learning system can store knowledge from past tasks and reuse it for longer tasks, researchers report
In a 2025 paper in Nature Machine Intelligence, researchers describe a robotic system that keeps learning as tasks arrive one at a time and later reuses that knowledge for longer jobs. The system…
- A simulated control method handles uneven input limits in multi-player nonlinear systems without a hard-to-find starting rule
Researchers at Bohai University and Southwest University report a control method for a class of continuous-time nonlinear systems with several controllers. In a 2024 paper in IEEE Transactions on…
- Fuzzy topological system shows higher accuracy on eleven regression datasets
In a 2025 paper in IEEE Transactions on Fuzzy Systems, researchers at Liaoning Shihua University report that a method called a hierarchical fuzzy topological system, or HFTS, showed higher accuracy…
- A 0.32-million-parameter adapter outperforms full fine-tuning and prompt learning in multimodal object tracking
In a 2024 paper in Proceedings of the AAAI Conference on Artificial Intelligence, a peer-reviewed conference, researchers at Tianjin University report a small adapter for object tracking. The adapter…
- Simulations show an optimization method reduced path interference in systems that use a reconfigurable intelligent surface for sensing and communication
In a 2025 paper in IEEE Journal on Selected Areas in Communications, a peer-reviewed journal, researchers at New York University Abu Dhabi and New York University modeled a base station that…
- Invalid action masking in policy gradient reinforcement learning has a theoretical basis and matters more as invalid actions grow, a 2022 study finds
In a 2022 paper published in Proceedings of the International Florida Artificial Intelligence Research Society Conference, a peer-reviewed conference, researchers at Drexel University examined a…
- Cooperative learning agents cut AI system recovery time by up to 47 percent in simulated and real-world-inspired failure scenarios
In a 2026 conference paper, researchers describe a self-healing AI system that uses several cooperating machine-learning agents to monitor systems, diagnose causes, and fix failures without a person…
- A self-driven AI agent showed stronger uncertainty control, steadier policy, and less behavior drift in open-world tasks
In a 2026 conference paper, researchers describe an intelligent agent that learns by exploring on its own and collecting knowledge. In open-world tasks, where conditions are not fixed, the agent…
- An autonomous drone won several races against each human champion and posted the fastest recorded race time
In a 2023 paper published in Nature, a peer-reviewed journal, researchers at the University of Zurich and Intel report that an autonomous system named Swift raced physical drones at the level of…
- Diffusion Policy outperformed comparison methods by 46.9 percent across 15 robot manipulation tasks
The authors report that Diffusion Policy, a way of choosing robot actions through a diffusion process, outperformed the methods they compared it with by an average of 46.9 percent across 15 tasks…
