Recent trends in Large Vision Language Models (LVLMs) research have been increasingly focusing on advancing beyond general image understanding towards more nuanced, object-level referential comprehension. In this paper, we present and delve into the self-consistency capability of LVLMs, a crucial aspect that reflects the models' ability to both generate informative captions for specific objects and subsequently utilize these captions to accurately re-identify the objects in a closed-loop process. This capability significantly mirrors the precision and reliability of fine-grained visual-language understanding. Our findings reveal that the self-consistency level of existing LVLMs falls short of expectations, posing limitations on their practical applicability and potential. To address this gap, we introduce a novel fine-tuning paradigm named Self-Consistency Tuning (SC-Tune). It features the synergistic learning of a cyclic describer-locator system. This paradigm is not only data-efficient but also exhibits generalizability across multiple LVLMs. Through extensive experiments, we demonstrate that SC-Tune significantly elevates performance across a spectrum of object-level vision-language benchmarks and maintains competitive or improved performance on image-level vision-language benchmarks. Both our model and code will be publicly available at https://github.com/ivattyue/SC-Tune.
Navigation in complex 3D scenarios requires appropriate environment representation for efficient scene understanding and trajectory generation. We propose a highly efficient and extensible global navigation framework based on a tomographic understanding of the environment to navigate ground robots in multi-layer structures. Our approach generates tomogram slices using the point cloud map to encode the geometric structure as ground and ceiling elevations. Then it evaluates the scene traversability considering the robot's motion capabilities. Both the tomogram construction and the scene evaluation are accelerated through parallel computation. Our approach further alleviates the trajectory generation complexity compared with planning in 3D spaces directly. It generates 3D trajectories by searching through multiple tomogram slices and separately adjusts the robot height to avoid overhangs. We evaluate our framework in various simulation scenarios and further test it in the real world on a quadrupedal robot. Our approach reduces the scene evaluation time by 3 orders of magnitude and improves the path planning speed by 3 times compared with existing approaches, demonstrating highly efficient global navigation in various complex 3D environments. The code is available at: https://github.com/byangw/PCT_planner.
Preference-based Reinforcement Learning (PbRL) avoids the need for reward engineering by harnessing human preferences as the reward signal. However, current PbRL algorithms over-reliance on high-quality feedback from domain experts, which results in a lack of robustness. In this paper, we present RIME, a robust PbRL algorithm for effective reward learning from noisy preferences. Our method incorporates a sample selection-based discriminator to dynamically filter denoised preferences for robust training. To mitigate the accumulated error caused by incorrect selection, we propose to warm start the reward model, which additionally bridges the performance gap during transition from pre-training to online training in PbRL. Our experiments on robotic manipulation and locomotion tasks demonstrate that RIME significantly enhances the robustness of the current state-of-the-art PbRL method. Ablation studies further demonstrate that the warm start is crucial for both robustness and feedback-efficiency in limited-feedback cases.
The rapid evolution of autonomous vehicles (AVs) has significantly influenced global transportation systems. In this context, we present ``Snow Lion'', an autonomous shuttle meticulously designed to revolutionize on-campus transportation, offering a safer and more efficient mobility solution for students, faculty, and visitors. The primary objective of this research is to enhance campus mobility by providing a reliable, efficient, and eco-friendly transportation solution that seamlessly integrates with existing infrastructure and meets the diverse needs of a university setting. To achieve this goal, we delve into the intricacies of the system design, encompassing sensing, perception, localization, planning, and control aspects. We evaluate the autonomous shuttle's performance in real-world scenarios, involving a 1146-kilometer road haul and the transportation of 442 passengers over a two-month period. These experiments demonstrate the effectiveness of our system and offer valuable insights into the intricate process of integrating an autonomous vehicle within campus shuttle operations. Furthermore, a thorough analysis of the lessons derived from this experience furnishes a valuable real-world case study, accompanied by recommendations for future research and development in the field of autonomous driving.
The smart morphing wing aircraft (SMWA) is a highly adaptable platform that can be widely used for intelligent warfare due to its real-time variable structure. The flexible conformal array (FCA) is a vital detection component of SMWA, when the deformation parameters of FCA are mismatched or array elements are mutually coupled, detection performance will be degraded. To overcome this problem and ensure robust beamforming for FCA, deviations in array control parameters (ACPs) and array perturbations, the effect of mutual coupling in addition to looking-direction errors should be considered. In this paper, we propose a robust adaptive beamforming (RAB) algorithm by reconstructing a multi-domain interference plus noise covariance matrix (INCM) and estimating steering vector (SV) for FCA. We first reconstruct the INCM using multi-domain processing, including ACP and angular domains. Then, SV estimation is executed through an optimization procedure. Experimental results have shown that the proposed beamformer outperforms existing beamformers in various mismatch conditions and harsh environments, such as high interference-to-noise ratios, and mutual coupling of antennas.
Considerable research efforts have been devoted to the development of motion planning algorithms, which form a cornerstone of the autonomous driving system (ADS). However, obtaining an interactive and secure trajectory for the ADS remains a formidable task, especially in scenarios with significant interaction complexities. Many contemporary prediction-based planning methods frequently overlook interaction modeling, leading to less effective planning performance. This paper introduces a novel prediction-based interactive planning framework that explicitly and mathematically models interactions among traffic entities during the planning process. Our method incorporates interaction reasoning into spatio-temporal (s-t) planning by defining interaction conditions and constraints. Furthermore, it records and continually updates interaction relations for each planned state throughout the forward search. We assess the performance of our approach alongside state-of-the-art methods using a series of experiments conducted in both single and multi-modal scenarios. These experiments encompass variations in the accuracy of prediction outcomes and different degrees of planner aggressiveness. The experimental findings demonstrate the effectiveness and robustness of our method, yielding insights applicable to the wider field of autonomous driving. For the community's reference, our code is accessible at https://github.com/ChenYingbing/IR-STP-Planner.
Accurate trajectory prediction is crucial for safe and efficient autonomous driving, but handling partial observations presents significant challenges. To address this, we propose a novel trajectory prediction framework called Partial Observations Prediction (POP) for congested urban road scenarios. The framework consists of two stages: self-supervised learning (SSL) and feature distillation. In SSL, a reconstruction branch reconstructs the hidden history of partial observations using a mask procedure and reconstruction head. The feature distillation stage transfers knowledge from a fully observed teacher model to a partially observed student model, improving prediction accuracy. POP achieves comparable results to top-performing methods in open-loop experiments and outperforms the baseline method in closed-loop simulations, including safety metrics. Qualitative results illustrate the superiority of POP in providing reasonable and safe trajectory predictions.
In recent years, imitation-based driving planners have reported considerable success. However, due to the absence of a standardized benchmark, the effectiveness of various designs remains unclear. The newly released nuPlan addresses this issue by offering a large-scale real-world dataset and a standardized closed-loop benchmark for equitable comparisons. Utilizing this platform, we conduct a comprehensive study on two fundamental yet underexplored aspects of imitation-based planners: the essential features for ego planning and the effective data augmentation techniques to reduce compounding errors. Furthermore, we highlight an imitation gap that has been overlooked by current learning systems. Finally, integrating our findings, we propose a strong baseline model-PlanTF. Our results demonstrate that a well-designed, purely imitation-based planner can achieve highly competitive performance compared to state-of-the-art methods involving hand-crafted rules and exhibit superior generalization capabilities in long-tail cases. Our models and benchmarks are publicly available. Project website https://jchengai.github.io/planTF.
Weakly-supervised action localization aims to recognize and localize action instancese in untrimmed videos with only video-level labels. Most existing models rely on multiple instance learning(MIL), where the predictions of unlabeled instances are supervised by classifying labeled bags. The MIL-based methods are relatively well studied with cogent performance achieved on classification but not on localization. Generally, they locate temporal regions by the video-level classification but overlook the temporal variations of feature semantics. To address this problem, we propose a novel attention-based hierarchically-structured latent model to learn the temporal variations of feature semantics. Specifically, our model entails two components, the first is an unsupervised change-points detection module that detects change-points by learning the latent representations of video features in a temporal hierarchy based on their rates of change, and the second is an attention-based classification model that selects the change-points of the foreground as the boundaries. To evaluate the effectiveness of our model, we conduct extensive experiments on two benchmark datasets, THUMOS-14 and ActivityNet-v1.3. The experiments show that our method outperforms current state-of-the-art methods, and even achieves comparable performance with fully-supervised methods.