Advanced interpretation of hyperspectral remote sensing images benefits many precise Earth observation tasks. Recently, visual foundation models have promoted the remote sensing interpretation but concentrating on RGB and multi-spectral images. Due to the varied hyperspectral channels, existing foundation models would face image-by-image tuning situation, imposing great pressure on hardware and time resources. In this paper, we propose a tuning-free hyper-spectral foundation model called HyperFree, by adapting the existing visual prompt engineering. To process varied channel numbers, we design a learned weight dictionary covering full-spectrum from 0.4 ∼ 2.5 μm, supporting to build the embedding layer dynamically. To make the prompt design more tractable, HyperFree can generate multiple semantic-aware masks for one prompt by treating feature distance as semantic-similarity. After pre-training HyperFree on constructed large-scale high-resolution hyperspectral images, HyperFree (1 prompt) has shown comparable results with specialized models (5 shots) on 5 tasks and 11 datasets. Code and dataset are accessible at https://rsidea.whu.edu.cn/hyperfree.htm.

We explore the problem of path planning for mobile robots in unknown environments using deep reinforcement learning (DRL). This paper proposes a multi-layer long short-term memory twin delayed deep deterministic policy gradient (MLTD3) algorithm for unknown environments. First, we introduce multi-layer long short-term memory (LSTM) networks to the actor network of the twin delayed deep deterministic policy gradient (TD3), to capture rich historical information to alleviate local optimal solutions in local path planning. Secondly, Poisson coding is employed in the state space to deal with the uncertainty of environments, so that the algorithm can discern the relationship within long sequence information. Then novel extrinsic and intrinsic reward functions are designed to avoid the dynamic obstacles in environments. Finally, the performance of the proposed algorithm is verified through simulations in ROS Gazebo and physical experiments in an unknown environment.

Remote sensing (RS) change detection (CD) refers to the difference of RS images at different times in the same geographic area. The method of using high-resolution RS images based on deep learning (DL) has the problem of poor domain adaptation (DA) under geographical isolation conditions, especially in the cropland scene with different phenology and planting type. Based on the universal Siamese network architecture, a multi-view domain confusion (MVDC) module is designed. The module performs discriminant operations on the generated source domain features and target, and guides the generator to generate more domain invariant features. The time consistency information is taken into account while the difference between geographical regions is reduced. The module can theoretically be plugged into any universal CD network. The experimental results show that the adaptive ability of multiple CD methods is improved after the addition of MVDC.

In this paper, we study the best achievable performance of a nonlinear system with an uncertain parameter vector in an output regulation problem. The nonlinear system is a stabilizable nonminimum phase system and its zero dynamics consists of a robust input-to-state stable component and an unstable but stabilizable component. It is assumed that the uncertain parameter vector, in the form of nonlinear functions, only appears in the robust input-to-state stable component of the zero dynamics and the linearizable part of the system. In the latter, the functions including the uncertain parameter satisfy a lower triangular structure. The performance considered in the output regulation problem for the uncertain nonlinear system is measured by the energy of its output. It is shown in this paper that the best achievable performance of the nonlinear system in the output regulation problem is only determined by the minimum energy of stabilizing the unstable component of its zero dynamics

In this work, we develop a switching design approach based on appropriate partition of the state space each associated with a base switching path. The resultant switching signal is the concatenation of a finite set of base paths triggered by state-feedback events. We prove that the switching signal makes the linear hybrid system both exponentially stable and robustly stable