This paper presents a trajectory planning method for wheeled robots with fixed steering axes while the steering angle of each wheel is constrained. In the past, All-Wheel-Steering(AWS) robots, incorporating modes such as rotation-free translation maneuvers, in-situ rotational maneuvers, and proportional steering, exhibited inefficient performance due to time-consuming mode switches. This inefficiency arises from wheel rotation constraints and inter-wheel cooperation requirements. The direct application of a holonomic moving strategy can lead to significant slip angles or even structural failure. Additionally, the limited steering range of AWS wheeled robots exacerbates nonlinearity issues, thereby complicating control processes. To address these challenges, we developed a novel planning method termed Constrained AWS(C-AWS), which integrates second-order discrete search with predictive control techniques. Experimental results demonstrate that our method adeptly generates feasible and smooth trajectories for C-AWS while adhering to steering angle constraints.
Computer-aided diagnosis systems hold great promise to aid radiologists and clinicians in radiological clinical practice and enhance diagnostic accuracy and efficiency. However, the conventional systems primarily focus on delivering diagnostic results through text report generation or medical image classification, positioning them as standalone decision-makers rather than helpers and ignoring radiologists' expertise. This study introduces an innovative paradigm to create an assistive co-pilot system for empowering radiologists by leveraging Large Language Models (LLMs) and medical image analysis tools. Specifically, we develop a collaborative framework to integrate LLMs and quantitative medical image analysis results generated by foundation models with radiologists in the loop, achieving efficient and safe generation of radiology reports and effective utilization of computational power of AI and the expertise of medical professionals. This approach empowers radiologists to generate more precise and detailed diagnostic reports, enhancing patient outcomes while reducing the burnout of clinicians. Our methodology underscores the potential of AI as a supportive tool in medical diagnostics, promoting a harmonious integration of technology and human expertise to advance the field of radiology.
3D lane detection plays a crucial role in autonomous driving by extracting structural and traffic information from the road in 3D space to assist the self-driving car in rational, safe, and comfortable path planning and motion control. Due to the consideration of sensor costs and the advantages of visual data in color information, in practical applications, 3D lane detection based on monocular vision is one of the important research directions in the field of autonomous driving, which has attracted more and more attention in both industry and academia. Unfortunately, recent progress in visual perception seems insufficient to develop completely reliable 3D lane detection algorithms, which also hinders the development of vision-based fully autonomous self-driving cars, i.e., achieving level 5 autonomous driving, driving like human-controlled cars. This is one of the conclusions drawn from this review paper: there is still a lot of room for improvement and significant improvements are still needed in the 3D lane detection algorithm for autonomous driving cars using visual sensors. Motivated by this, this review defines, analyzes, and reviews the current achievements in the field of 3D lane detection research, and the vast majority of the current progress relies heavily on computationally complex deep learning models. In addition, this review covers the 3D lane detection pipeline, investigates the performance of state-of-the-art algorithms, analyzes the time complexity of cutting-edge modeling choices, and highlights the main achievements and limitations of current research efforts. The survey also includes a comprehensive discussion of available 3D lane detection datasets and the challenges that researchers have faced but have not yet resolved. Finally, our work outlines future research directions and welcomes researchers and practitioners to enter this exciting field.
Can computers perceive the physical properties of objects solely through vision? Research in cognitive science and vision science has shown that humans excel at identifying materials and estimating their physical properties based purely on visual appearance. In this paper, we present a novel approach for dense prediction of the physical properties of objects using a collection of images. Inspired by how humans reason about physics through vision, we leverage large language models to propose candidate materials for each object. We then construct a language-embedded point cloud and estimate the physical properties of each 3D point using a zero-shot kernel regression approach. Our method is accurate, annotation-free, and applicable to any object in the open world. Experiments demonstrate the effectiveness of the proposed approach in various physical property reasoning tasks, such as estimating the mass of common objects, as well as other properties like friction and hardness.
Maps provide robots with crucial environmental knowledge, thereby enabling them to perform interactive tasks effectively. Easily accessing accurate abstract-to-detailed geometric and semantic concepts from maps is crucial for robots to make informed and efficient decisions. To comprehensively model the environment and effectively manage the map data structure, we propose DHP-Mapping, a dense mapping system that utilizes multiple Truncated Signed Distance Field (TSDF) submaps and panoptic labels to hierarchically model the environment. The output map is able to maintain both voxel- and submap-level metric and semantic information. Two modules are presented to enhance the mapping efficiency and label consistency: (1) an inter-submaps label fusion strategy to eliminate duplicate points across submaps and (2) a conditional random field (CRF) based approach to enhance panoptic labels through object label comprehension and contextual information. We conducted experiments with two public datasets including indoor and outdoor scenarios. Our system performs comparably to state-of-the-art (SOTA) methods across geometry and label accuracy evaluation metrics. The experiment results highlight the effectiveness and scalability of our system, as it is capable of constructing precise geometry and maintaining consistent panoptic labels. Our code is publicly available at https://github.com/hutslib/DHP-Mapping.
The scaling laws and extraordinary performance of large foundation models motivate the development and utilization of such large models in biomedicine. However, despite early promising results on some biomedical benchmarks, there are still major challenges that need to be addressed before these models can be used in real-world applications. Frontier models such as GPT-4V still have major competency gaps in multimodal capabilities for biomedical applications. Moreover, pragmatic issues such as access, cost, latency, and compliance make it hard for clinicians to use privately-hosted state-of-the-art large models directly on private patient data. In this paper, we explore training open-source small multimodal models (SMMs) to bridge biomedical competency gaps for unmet clinical needs. To maximize data efficiency, we adopt a modular approach by incorporating state-of-the-art pre-trained models for image and text modalities, and focusing on training a lightweight adapter to ground each modality to the text embedding space. We conduct a comprehensive study of this approach on radiology imaging. For training, we assemble a large dataset with over 1 million image-text pairs. For evaluation, we propose a clinically driven novel approach using GPT-4 and demonstrate its parity with expert evaluation. We also study grounding qualitatively using attention. For best practice, we conduct a systematic ablation study on various choices in data engineering and multimodal training. The resulting LLaVA-Rad (7B) model attains state-of-the-art results on radiology tasks such as report generation and cross-modal retrieval, even outperforming much larger models such as GPT-4V and Med-PaLM M (84B). LLaVA-Rad is fast and can be run on a single V100 GPU in private settings, offering a promising state-of-the-art tool for real-world clinical applications.
Multiple cameras can provide multi-view video coverage of a person. It is necessary to fuse multi-view data, e.g., for subsequent behavioral analysis, while such fusion often relies on calibration of cameras in traditional solutions. However, it is non-trivial to calibrate multiple cameras. In this work, we propose a method to reconstruct 3D human body from multiple uncalibrated camera views. First, we adopt a pre-trained human body encoder to process each individual camera view, such that human body models and parameters can be reconstructed for each view. Next, instead of simply averaging models across views, we train a network to determine the weights of individual views for their fusion, based on the parameters estimated for joints and hands of human body as well as camera positions. Further, we turn to the mesh surface of human body for dynamic fusion, such that facial expression can be seamlessly integrated into the model of human body. Our method has demonstrated superior performance in reconstructing human body upon two public datasets. More importantly, our method can flexibly support ad-hoc deployment of an arbitrary number of cameras, which has significant potential in related applications. We will release source code upon acceptance of the paper.
Automatic thin-prep cytologic test (TCT) screening can assist pathologists in finding cervical abnormality towards accurate and efficient cervical cancer diagnosis. Current automatic TCT screening systems mostly involve abnormal cervical cell detection, which generally requires large-scale and diverse training data with high-quality annotations to achieve promising performance. Pathological image synthesis is naturally raised to minimize the efforts in data collection and annotation. However, it is challenging to generate realistic large-size cytopathological images while simultaneously synthesizing visually plausible appearances for small-size abnormal cervical cells. In this paper, we propose a two-stage image synthesis framework to create synthetic data for augmenting cervical abnormality screening. In the first Global Image Generation stage, a Normal Image Generator is designed to generate cytopathological images full of normal cervical cells. In the second Local Cell Editing stage, normal cells are randomly selected from the generated images and then are converted to different types of abnormal cells using the proposed Abnormal Cell Synthesizer. Both Normal Image Generator and Abnormal Cell Synthesizer are built upon Stable Diffusion, a pre-trained foundation model for image synthesis, via parameter-efficient fine-tuning methods for customizing cytopathological image contents and extending spatial layout controllability, respectively. Our experiments demonstrate the synthetic image quality, diversity, and controllability of the proposed synthesis framework, and validate its data augmentation effectiveness in enhancing the performance of abnormal cervical cell detection.
With the remarkable capabilities, large language models (LLMs) have emerged as essential elements in numerous NLP applications, while parameter-efficient finetuning, especially LoRA, has gained popularity as a lightweight approach for model customization. Meanwhile, various dropout methods, initially designed for full finetuning with all the parameters updated, alleviates overfitting associated with excessive parameter redundancy. Hence, a possible contradiction arises from negligible trainable parameters of LoRA and the effectiveness of previous dropout methods, which has been largely overlooked. To fill this gap, we first confirm that parameter-efficient LoRA is also overfitting-prone. We then revisit transformer-specific dropout methods, and establish their equivalence and distinctions mathematically and empirically. Building upon this comparative analysis, we introduce a unified framework for a comprehensive investigation, which instantiates these methods based on dropping position, structural pattern and compensation measure. Through this framework, we reveal the new preferences and performance comparisons of them when involved with limited trainable parameters. This framework also allows us to amalgamate the most favorable aspects into a novel dropout method named HiddenKey. Extensive experiments verify the remarkable superiority and sufficiency of HiddenKey across multiple models and tasks, which highlights it as the preferred approach for high-performance and parameter-efficient finetuning of LLMs.