Search

Wheeled-legged robots offer significant mobility and versatility but face substantial challenges when operating on slippery terrains. Traditional model-based controllers for these robots assume no slipping. While reinforcement learning (RL) helps quadruped robots adapt to different surfaces, recovering from slips remains challenging, especially for systems with few contact points. Estimating the ground friction coefficient is another open challenge. In this paper, we propose a novel friction-aware safety locomotion framework that integrates Large Vision Language Models (LVLMs) with a RL policy. Our approach explicitly incorporates the estimated friction coefficient into the RL policy, enabling the robot to adapt its behavior in advance based on the surface type before reaching it. We introduce a Friction-From-Vision (FFV) module, which leverages LVLMs to estimate ground friction coefficients, eliminating the need for large datasets and extensive training. The framework was validated on a customized wheeled inverted pendulum, and experimental results demonstrate that our framework increases the success rate in completing driving tasks by adjusting speed according to terrain type, while achieving better tracking performance compared to baseline methods. Our framework can be simply integrated with any other RL policies., Comment: submitted to icra2025

Recent advances in vision-language foundational models, such as CLIP, have demonstrated significant strides in zero-shot classification. However, the extensive parameterization of models like CLIP necessitates a resource-intensive fine-tuning process. In response, TIP-Adapter and SuS-X have introduced training-free methods aimed at bolstering the efficacy of downstream tasks. While these approaches incorporate support sets to maintain data distribution consistency between knowledge cache and test sets, they often fall short in terms of generalization on the test set, particularly when faced with test data exhibiting substantial distributional variations. In this work, we present CapS-Adapter, an innovative method that employs a caption-based support set, effectively harnessing both image and caption features to exceed existing state-of-the-art techniques in training-free scenarios. CapS-Adapter adeptly constructs support sets that closely mirror target distributions, utilizing instance-level distribution features extracted from multimodal large models. By leveraging CLIP's single and cross-modal strengths, CapS-Adapter enhances predictive accuracy through the use of multimodal support sets. Our method achieves outstanding zero-shot classification results across 19 benchmark datasets, improving accuracy by 2.19\% over the previous leading method. Our contributions are substantiated through extensive validation on multiple benchmark datasets, demonstrating superior performance and robust generalization capabilities. Our code is made publicly available at https://github.com/WLuLi/CapS-Adapter., Comment: ACM Multimedia 2024 Poster

Random numbers are widely used for information security, cryptography, stochastic modeling, and quantum simulations. Key technical challenges for physical random number generation are speed and scalability. We demonstrate a method for ultrafast generation of hundreds of random bit streams in parallel with a single laser diode. Spatio-temporal interference of many lasing modes in a specially designed cavity is introduced as a scheme for greatly accelerated random bit generation. Spontaneous emission, caused by quantum fluctuations, produces stochastic noise that makes the bit streams unpredictable. We achieve a total bit rate of 250 terabits per second with off-line post-processing, which is more than two orders of magnitude higher than the current post-processing record. Our approach is robust, compact, and energy efficient with potential applications in secure communication and high-performance computation.

Recently, Chi Xu et al. predicted the phase-filling singularities (PFS) in the optical dielectric function (ODF) of the highly doped $n$-type Ge and confirmed in experiment the PFS associated $E_{1}+\Delta_{1}$ transition by advanced \textit{in situ} doping technology [Phys. Rev. Lett. 118, 267402 (2017)], but the strong overlap between $E_{1}$ and $E_{1}+\Delta_{1}$ optical transitions made the PFS associated $E_{1}$ transition that occurs at the high doping concentration unobservable in their measurement. In this work, we investigate the PFS of the highly doped n-type Ge in the presence of the uniaxial and biaxial tensile strain along [100], [110] and [111] crystal orientation. Compared with the relaxed bulk Ge, the tensile strain along [100] increases the energy separation between the $E_{1}$ and $E_{1}+\Delta_{1}$ transition, making it possible to reveal the PFS associated $E_{1}$ transition in optical measurement. Besides, the application of tensile strain along [110] and [111] offers the possibility of lowering the required doping concentration for the PFS to be observed, resulting in new additional features associated with $E_{1}+\Delta_{1}$ transition at inequivalent $L$-valleys. These theoretical predications with more distinguishable optical transition features in the presence of the uniaxial and biaxial tensile strain can be more conveniently observed in experiment, providing new insights into the excited states in heavily doped semiconductors., Comment: 5 pages, 5 figures

We extend the previous 30-band $k$$\cdot$$p$ model effectively employed for relaxed Ge$_{1-x}$Sn$_{x}$ alloy to the case of strained Ge$_{1-x}$Sn$_{x}$ alloy. The strain-relevant parameters for the 30-band $k$$\cdot$$p$ model are obtained by using linear interpolation between the values of single crystal of Ge and Sn that are from literatures and optimizations. We specially investigate the dependence of band-gap at $L$-valley and $\Gamma$-valley with different Sn composition under uniaxial and biaxial strain along [100], [110] and [111] directions. The good agreement between our theoretical predictions and experimental data validates the effectiveness of our model. Our 30-band $k$$\cdot$$p$ model and relevant input parameters successfully applied to relaxed and strained Ge$_{1-x}$Sn$_{x}$ alloy offers a powerful tool for the optimization of sophisticated devices made from such alloy., Comment: 8-pages, 6 figures

We design and fabricate an on-chip laser source that produces a directional beam with low spatial coherence. The lasing modes are based on the axial orbit in a stable cavity and have good directionality. To reduce the spatial coherence of emission, the number of transverse lasing modes is maximized by fine-tuning the cavity geometry. Decoherence is reached in a few nanoseconds. Such rapid decoherence will facilitate applications in ultrafast speckle-free full-field imaging.

Recently emerged dielectric resonators and metasurfaces offer a low-loss platform for efficient manipulation of electromagnetic waves from microwave to visible. Such flat meta-optics can focus electromagnetic waves, generate structured beams and vortices, enhance local fields for sensing as well as provide additional functionalities for advanced MRI machinery. Recent advances are associated with exotic optical modes called bound states in the continuum, which can give rise to extremely large quality factors and supercavity lasing. Here, we experimentally demonstrate subwavelength active supercavities with extremely high-Q resonances that could be reconfigured at an ultrafast time scale. We reveal that such supercavities enable all-optical switching and modulation of extremely sharp resonances, and thus could have numerous applications in lasing, mode multiplexing, and biosensing.