Open-vocabulary mobile manipulation (OVMM) that involves the handling of novel and unseen objects across different workspaces remains a significant challenge for real-world robotic applications. In this paper, we propose a novel Language-conditioned Open-Vocabulary Mobile Manipulation framework, named LOVMM, incorporating the large language model (LLM) and vision-language model (VLM) to tackle various mobile manipulation tasks in household environments. Our approach is capable of solving various OVMM tasks with free-form natural language instructions (e.g. "toss the food boxes on the office room desk to the trash bin in the corner", and "pack the bottles from the bed to the box in the guestroom"). Extensive experiments simulated in complex household environments show strong zero-shot generalization and multi-task learning abilities of LOVMM. Moreover, our approach can also generalize to multiple tabletop manipulation tasks and achieve better success rates compared to other state-of-the-art methods.

A unified model for L-band fully polarimatric ocean scattering and emission with directional asymmetries is proposed in this paper. The model framework is based on the two-scale polarimetric scattering model. Three wave spectra, i.e., the Durden-Vesecky spectrum, Elfouhaily Spectrum and KHCC03 spectrum, are employed for to account for the surface slopes of large-scale waves, spectrum of small-scale waves, and wave breaking effects, respectively. For the foam contribution for ocean emission at high wind speeds, the Anguelova and Gaiser, 2013 (AG13) foam emission model and a newly proposed foam coverage model are utilized. The model is validated against the fully polarimetric measurements of ocean scattering and emission of the Aquarius and SMAP mission. Numerical results show that the unified model can well simulate the opposite anisotropies of both ocean scattering and emission at low and high wind speeds. The model accuracies on directional properties of ocean scattering and wind-driven emission are less than of about 1 dB and 0.15 K, respectively.

Synthetic aperture radar (SAR) plays an essential role in earth observation and projection due to its capability to penetrate clouds, which makes it possible to monitor terrestrial surfaces under all weather conditions. Multiplicative noise often occurs in the SAR signal, hampering the retrieval of information from SAR imagery. Convolutional neural networks (CNNs) have been used in many computer vision tasks and are helpful in image denoising. However, current CNN-based denoising approaches inevitably lead to a “washed out” effect that loses spatial details. Another limitation is that most typical CNN-based denoising models require a noise-free image for training. To address these issues, we propose a novel end-to-end self-supervised SAR denoising model: Enhanced Noise2Noise (EN2N), which can be trained without a noise-free image. To enhance the quality of the result images, the perceptual features from a pre-learned CNN are introduced to restore the spatial details by a hybrid loss function. Experiments show that our proposed method outperforms the typical denoising methods in terms of noise reduction and feature preservation based on image quality metrics. Also, the new hybrid loss could enhance the spatial details significantly. The good performance maintains the robustness throughout time, which reduces the uncertainty in time-series SAR caused by random noise. Benefiting from optimization of graphics processing unit (GPU) and multi-threading, the proposed method has higher computation efficiency than traditional methods. This study demonstrates the great potential of using our self-supervised deep learning approaches for SAR image denoising in the future.