Intelligent robot is the ultimate goal in the robotics field. Existing works leverage learning-based or optimization-based methods to accomplish human-defined tasks. However, the challenge of enabling robots to explore various environments autonomously remains unresolved. In this work, we propose a framework named GExp, which endows robots with the capability of exploring and learning autonomously without human intervention. To achieve this goal, we devise modules including self-exploration, knowledge-base-building, and close-loop feedback based on foundation models. Inspired by the way that infants interact with the world, GExp encourages robots to understand and explore the environment with a series of self-generated tasks. During the process of exploration, the robot will acquire skills from experiences that are useful in the future. GExp provides robots with the ability to solve complex tasks through self-exploration. GExp work is independent of prior interactive knowledge and human intervention, allowing it to adapt directly to different scenarios, unlike previous studies that provided in-context examples as few-shot learning. In addition, we propose a workflow of deploying the real-world robot system with self-learned skills as an embodied assistant. Project website: GExp.com.

Power sources and energy-harvesting schemes are still grand challenges for soft robots. Notably, compared with other power sources, triboelectric nanogenerators (TENGs) have shown great potential because of their low manufacturing and fabrication costs, outstanding resilience, remarkable stability, and environmental friendliness. Herein, a triboelectric effect-driven piezoelectric soft robot (TEPSR) system is proposed, which integrates a rotary freestanding triboelectric nanogenerator (RF-TENG) to drive a soft robot comprising a piezoelectric unimorph and electrostatic footpads. Based on the natural triboelectrification, through converting mechanical energy into electricity, TENG provides a unique approach for actuation and manipulation of the soft robot. The perfect combination provides the most straightforward way for creating a self-powered system. Experimentally, under the power of RF-TENG, the soft robot reaches a maximum moving speed of 10 cm per second and a turning rate of 89.7° per second, respectively. The actuation and manipulation demonstration are intuitively accomplished by maneuvering the robot around a maze with a 71 cm track within 28 s. For autonomous feedback controls, one practical application is carrying two infrared sensors on board to realize obstacle avoidance in an unstructured environment. Moreover, a micro-camera was equipped with the soft robot to provide real-time “first-person” video streaming, enhancing its detection capability.

As pioneering information technology, the Internet of Things (IoT) targets at building an infrastructure of embedded devices and networks of connected objects, to offer omnipresent ecosystem and interaction across billions of smart devices, sensors, and actuators. The deployment of IoT calls for decentralized power supplies, self-powered sensors, and wireless transmission technologies, which have brought both opportunities and challenges to the existing solutions, especially when the network scales up. The Triboelectric Nanogenerators (TENGs), recently developed for mechanical energy harvesting and mechanical-to-electrical signal conversion, have the natural properties of energy and information, which have demonstrated high potentials in various applications of IoT. This context provides a comprehensive review of TENG enabled IoT and discusses the most popular and significant divisions. Firstly, the basic principle of TENG is re-examined in this article. Subsequently, a comprehensive and detailed review is given to the concept of IoT, followed by the scientific development of the TENG enabled IoT. Finally, the future of this evolving area is addressed.