VIRT: Vision Instructed Transformer for Robotic Manipulation

Robotic manipulation, owing to its multi-modal nature, often faces significant training ambiguity, necessitating explicit instructions to clearly delineate the manipulation details in tasks. In this work, we highlight that vision instruction is naturally more comprehensible to recent robotic policies than the commonly adopted text instruction, as these policies are born with some vision understanding ability like human infants. Building on this premise and drawing inspiration from cognitive science, we introduce the robotic imagery paradigm, which realizes large-scale robotic data pre-training without text annotations. Additionally, we propose the robotic gaze strategy that emulates the human eye gaze mechanism, thereby guiding subsequent actions and focusing the attention of the policy on the manipulated object. Leveraging these innovations, we develop VIRT, a fully Transformer-based policy. We design comprehensive tasks using both a physical robot and simulated environments to assess the efficacy of VIRT. The results indicate that VIRT can complete very competitive tasks like ``opening the lid of a tightly sealed bottle'', and the proposed techniques boost the success rates of the baseline policy on diverse challenging tasks from nearly 0% to more than 65%.

FP-VEC: Fingerprinting Large Language Models via Efficient Vector Addition

Training Large Language Models (LLMs) requires immense computational power and vast amounts of data. As a result, protecting the intellectual property of these models through fingerprinting is essential for ownership authentication. While adding fingerprints to LLMs through fine-tuning has been attempted, it remains costly and unscalable. In this paper, we introduce FP-VEC, a pilot study on using fingerprint vectors as an efficient fingerprinting method for LLMs. Our approach generates a fingerprint vector that represents a confidential signature embedded in the model, allowing the same fingerprint to be seamlessly incorporated into an unlimited number of LLMs via vector addition. Results on several LLMs show that FP-VEC is lightweight by running on CPU-only devices for fingerprinting, scalable with a single training and unlimited fingerprinting process, and preserves the model's normal behavior. The project page is available at https://fingerprintvector.github.io .

LARM: Large Auto-Regressive Model for Long-Horizon Embodied Intelligence

Due to the need to interact with the real world, embodied agents are required to possess comprehensive prior knowledge, long-horizon planning capability, and a swift response speed. Despite recent large language model (LLM) based agents achieving promising performance, they still exhibit several limitations. For instance, the output of LLMs is a descriptive sentence, which is ambiguous when determining specific actions. To address these limitations, we introduce the large auto-regressive model (LARM). LARM leverages both text and multi-view images as input and predicts subsequent actions in an auto-regressive manner. To train LARM, we develop a novel data format named auto-regressive node transmission structure and assemble a corresponding dataset. Adopting a two-phase training regimen, LARM successfully harvests enchanted equipment in Minecraft, which demands significantly more complex decision-making chains than the highest achievements of prior best methods. Besides, the speed of LARM is 6.8x faster.

DriveGPT4: Interpretable End-to-end Autonomous Driving via Large Language Model

In the past decade, autonomous driving has experienced rapid development in both academia and industry. However, its limited interpretability remains a significant unsolved problem, severely hindering autonomous vehicle commercialization and further development. Previous approaches utilizing small language models have failed to address this issue due to their lack of flexibility, generalization ability, and robustness. Recently, multimodal large language models (LLMs) have gained considerable attention from the research community for their capability to process and reason non-text data (e.g., images and videos) by text. In this paper, we present DriveGPT4, an interpretable end-to-end autonomous driving system utilizing LLMs. DriveGPT4 is capable of interpreting vehicle actions and providing corresponding reasoning, as well as answering diverse questions posed by human users for enhanced interaction. Additionally, DriveGPT4 predicts vehicle low-level control signals in an end-to-end fashion. These capabilities stem from a customized visual instruction tuning dataset specifically designed for autonomous driving. To the best of our knowledge, DriveGPT4 is the first work focusing on interpretable end-to-end autonomous driving. When evaluated on multiple tasks alongside conventional methods and video understanding LLMs, DriveGPT4 demonstrates superior qualitative and quantitative performance. Additionally, DriveGPT4 can be generalized in a zero-shot fashion to accommodate more unseen scenarios. The project page is available at https://tonyxuqaq.github.io/projects/DriveGPT4/ .

InsightMapper: A Closer Look at Inner-instance Information for Vectorized High-Definition Mapping

Vectorized high-definition (HD) maps contain detailed information about surrounding road elements, which are crucial for various downstream tasks in modern autonomous driving vehicles, such as vehicle planning and control. Recent works have attempted to directly detect the vectorized HD map as a point set prediction task, resulting in significant improvements in detection performance. However, these approaches fail to analyze and exploit the inner-instance correlations between predicted points, impeding further advancements. To address these challenges, we investigate the utilization of inner-$\textbf{INS}$tance information for vectorized h$\textbf{IGH}$-definition mapping through $\textbf{T}$ransformers and introduce InsightMapper. This paper presents three novel designs within InsightMapper that leverage inner-instance information in distinct ways, including hybrid query generation, inner-instance query fusion, and inner-instance feature aggregation. Comparative experiments are conducted on the NuScenes dataset, showcasing the superiority of our proposed method. InsightMapper surpasses previous state-of-the-art (SOTA) methods by 5.78 mAP and 5.12 TOPO, which assess topology correctness. Simultaneously, InsightMapper maintains high efficiency during both training and inference phases, resulting in remarkable comprehensive performance. The project page for this work is available at https://tonyxuqaq.github.io/projects/InsightMapper .

FSNet: Redesign Self-Supervised MonoDepth for Full-Scale Depth Prediction for Autonomous Driving

Predicting accurate depth with monocular images is important for low-cost robotic applications and autonomous driving. This study proposes a comprehensive self-supervised framework for accurate scale-aware depth prediction on autonomous driving scenes utilizing inter-frame poses obtained from inertial measurements. In particular, we introduce a Full-Scale depth prediction network named FSNet. FSNet contains four important improvements over existing self-supervised models: (1) a multichannel output representation for stable training of depth prediction in driving scenarios, (2) an optical-flow-based mask designed for dynamic object removal, (3) a self-distillation training strategy to augment the training process, and (4) an optimization-based post-processing algorithm in test time, fusing the results from visual odometry. With this framework, robots and vehicles with only one well-calibrated camera can collect sequences of training image frames and camera poses, and infer accurate 3D depths of the environment without extra labeling work or 3D data. Extensive experiments on the KITTI dataset, KITTI-360 dataset and the nuScenes dataset demonstrate the potential of FSNet. More visualizations are presented in \url{https://sites.google.com/view/fsnet/home}

RNGDet++: Road Network Graph Detection by Transformer with Instance Segmentation and Multi-scale Features Enhancement

The graph structure of road networks is critical for downstream tasks of autonomous driving systems, such as global planning, motion prediction and control. In the past, the road network graph is usually manually annotated by human experts, which is time-consuming and labor-intensive. To obtain the road network graph with better effectiveness and efficiency, automatic approaches for road network graph detection are required. Previous works either post-process semantic segmentation maps or propose graph-based algorithms to directly predict the road network graph. However, previous works suffer from hard-coded heuristic processing algorithms and inferior final performance. To enhance the previous SOTA (State-of-the-Art) approach RNGDet, we add an instance segmentation head to better supervise the model training, and enable the model to leverage multi-scale features of the backbone network. Since the new proposed approach is improved from RNGDet, it is named RNGDet++. All approaches are evaluated on a large publicly available dataset. RNGDet++ outperforms baseline models on almost all metrics scores. It improves the topology correctness APLS (Average Path Length Similarity) by around 3\%. The demo video and supplementary materials are available on our project page \url{https://tonyxuqaq.github.io/projects/RNGDetPlusPlus/}.

V2HDM-Mono: A Framework of Building a Marking-Level HD Map with One or More Monocular Cameras

Marking-level high-definition maps (HD maps) are of great significance for autonomous vehicles, especially in large-scale, appearance-changing scenarios where autonomous vehicles rely on markings for localization and lanes for safe driving. In this paper, we propose a highly feasible framework for automatically building a marking-level HD map using a simple sensor setup (one or more monocular cameras). We optimize the position of the marking corners to fit the result of marking segmentation and simultaneously optimize the inverse perspective mapping (IPM) matrix of the corresponding camera to obtain an accurate transformation from the front view image to the bird's-eye view (BEV). In the quantitative evaluation, the built HD map almost attains centimeter-level accuracy. The accuracy of the optimized IPM matrix is similar to that of the manual calibration. The method can also be generalized to build HD maps in a broader sense by increasing the types of recognizable markings.

CenterLineDet: Road Lane CenterLine Graph Detection With Vehicle-Mounted Sensors by Transformer for High-definition Map Creation

With the rapid development of autonomous vehicles, there witnesses a booming demand for high-definition maps (HD maps) that provide reliable and robust prior information of static surroundings in autonomous driving scenarios. As one of the main high-level elements in the HD map, the road lane centerline is critical for downstream tasks, such as prediction and planning. Manually annotating lane centerline HD maps by human annotators is labor-intensive, expensive and inefficient, severely restricting the wide application and fast deployment of autonomous driving systems. Previous works seldom explore the centerline HD map mapping problem due to the complicated topology and severe overlapping issues of road centerlines. In this paper, we propose a novel method named CenterLineDet to create the lane centerline HD map automatically. CenterLineDet is trained by imitation learning and can effectively detect the graph of lane centerlines by iterations with vehicle-mounted sensors. Due to the application of the DETR-like transformer network, CenterLineDet can handle complicated graph topology, such as lane intersections. The proposed approach is evaluated on a large publicly available dataset Nuscenes, and the superiority of CenterLineDet is well demonstrated by the comparison results. This paper is accompanied by a demo video and a supplementary document that are available at \url{https://tonyxuqaq.github.io/projects/CenterLineDet/}.

RNGDet: Road Network Graph Detection by Transformer in Aerial Images

Road network graphs provide critical information for autonomous vehicle applications, such as motion planning on drivable areas. However, manually annotating road network graphs is inefficient and labor-intensive. Automatically detecting road network graphs could alleviate this issue, but existing works are either segmentation-based approaches that could not ensure satisfactory topology correctness, or graph-based approaches that could not present precise enough detection results. To provide a solution to these problems, we propose a novel approach based on transformer and imitation learning named RNGDet (\underline{R}oad \underline{N}etwork \underline{G}raph \underline{Det}ection by Transformer) in this paper. In view of that high-resolution aerial images could be easily accessed all over the world nowadays, we make use of aerial images in our approach. Taken as input an aerial image, our approach iteratively generates road network graphs vertex-by-vertex. Our approach can handle complicated intersection points of various numbers of road segments. We evaluate our approach on a publicly available dataset. The superiority of our approach is demonstrated through the comparative experiments.