Surface information acquisition by robots faces challenges such as sensor uncertainty, limited resources, and dynamic environment, all of which often lead to reduced collection efficiency and accuracy. To address these issues, this paper proposes a Risk-aware Informative Path Planning (RIPP) framework. The framework is capable of adaptively selecting the target region according to the mutual information between the expected detection viewpoints. The uncertainty risk caused by noisy sensing can be effectively managed using the Conditional Value at Risk (CVaR)-based method. Therefore, a CVaR-based Greedy Algorithm (CGA) is proposed to select the optimal set of inspection viewpoints. To further enhance information acquisition efficiency, the drone’s path is optimized using a novel Adaptive Fractional Particle Swarm Optimization (AFPSO) algorithm. This approach enables the drone to autonomously select trajectories rich in high-value information. This framework is evaluated in the context of 3D surface temperature inspection of large storage tanks. Simulation and experimental results show that RIPP framework significantly reduces information reconstruction errors in tank surface inspections by demonstrating clear advantages over existing methods. The effectiveness and feasibility of RIPP framework in surface information acquisition task are verified, which provides a new solution for efficient monitoring in complex environment.

Hashing technology has an excellent high dimensional visual information encoding ability. It can map distance information from high dimensional to low dimensional Hamming space, which is widely used in large-scale image nearest neighbor search tasks. Most recent studies, such as pair-wise and tripletwise, use local positional relations to construct hashing functions. These learning methods, which are only based on local information, will lead to an incoherent feature representation, especially for semantic similarity features. Therefore, we propose a global distance estimation hashing (DEH). The DEH establishes a deep hashing model by constructing global distance relations that can define a distance between every paired category. Thus the distance relations constructed by DEH include much more detailed information. In other words, DEH focuses on global distance relations and makes the division of boundaries have excellent performance, especially for those samples with subtle changes. After the mapping, the model quantization approach effectively decreases the quantization loss caused by transitioning from the real-valued space to the Hamming space. Numerous experiments show that our DEH achieves excellent results on CIFAR-10, NUS-WIDE and ImageNet. These achievements not only validate the effectiveness of DEH in general image hashing retrieval tasks but also demonstrate its significant advantages in handling the large-scale multimedia retrieval systems.

In order to collect mechanical energy in the environment for self-powered sensor applications, a self-powered capacitive pressure sensor with liquid alloy composite as electrode is developed based on triboelectric nanogenerator (TENG). A micro-pyramid structure is fabricated on the surface of polydimethylsiloxane (PDMS) to improve the performance of the pressure sensor. Test results show that the sensitivity of the pressure sensor is increased by 86.26% compared with the sensor without the micro-pyramid structure. The sensor also has an outstanding output performance. When resistance is 100 MΩ, power output has reached nearly 64 μW.