Linlin Ou

Xinyi Yu, Jianan Hu, Yuehai Fan et al.

Robot navigation in dynamic environments shared with humans is an important but challenging task, which suffers from performance deterioration as the crowd grows. In this paper, multi-subgoal robot navigation approach based on deep reinforcement learning is proposed, which can reason about more comprehensive relationships among all agents (robot and humans). Specifically, the next position point is planned for the robot by introducing history information and interactions in our work. Firstly, based on subgraph network, the history information of all agents is aggregated before encoding interactions through a graph neural network, so as to improve the ability of the robot to anticipate the future scenarios implicitly. Further consideration, in order to reduce the probability of unreliable next position points, the selection module is designed after policy network in the reinforcement learning framework. In addition, the next position point generated from the selection module satisfied the task requirements better than that obtained directly from the policy network. The experiments demonstrate that our approach outperforms state-of-the-art approaches in terms of both success rate and collision rate, especially in crowded human environments.

Xinyi Yu, Jiangping Lu, Xinyi Yu et al.

Oriented bounding box regression is crucial for oriented object detection. However, regression-based methods often suffer from boundary problems and the inconsistency between loss and evaluation metrics. In this paper, a modulated Kalman IoU loss of approximate SkewIoU is proposed, named MKIoU. To avoid boundary problems, we convert the oriented bounding box to Gaussian distribution, then use the Kalman filter to approximate the intersection area. However, there exists significant difference between the calculated and actual intersection areas. Thus, we propose a modulation factor to adjust the sensitivity of angle deviation and width-height offset to loss variation, making the loss more consistent with the evaluation metric. Furthermore, the Gaussian modeling method avoids the boundary problem but causes the angle confusion of square objects simultaneously. Thus, the Gaussian Angle Loss (GA Loss) is presented to solve this problem by adding a corrected loss for square targets. The proposed GA Loss can be easily extended to other Gaussian-based methods. Experiments on three publicly available aerial image datasets, DOTA, UCAS-AOD, and HRSC2016, show the effectiveness of the proposed method.

Mingyang Zhang, Hao Chen, Chunhua Shen et al.

Large Language Models (LLMs), such as LLaMA and T5, have shown exceptional performance across various tasks through fine-tuning. Although low-rank adaption (LoRA) has emerged to cheaply fine-tune these LLMs on downstream tasks, their deployment is still hindered by the vast model scale and computational costs. Post-training model pruning offers a way to compress LLMs. However, the current pruning methods designed for LLMs are not compatible with LoRA. This is due to their utilization of unstructured pruning on LLMs, impeding the merging of LoRA weights, or their dependence on the gradients of pre-trained weights to guide pruning, which can impose significant memory overhead. To this end, we propose LoRAPrune, a new framework that delivers an accurate structured pruned model in a highly memory-efficient manner. Specifically, we first design a LoRA-guided pruning criterion, which uses the weights and gradients of LoRA, rather than the gradients of pre-trained weights for importance estimation. We subsequently integrate this criterion into an iterative pruning process, effectively removing redundant channels and heads. Extensive experimental results demonstrate the superior performance of our LoRAPrune over existing approaches on the LLaMA series models. At a 50\% compression rate, LoRAPrune demonstrates superior performance over LLM-Pruner, achieving a reduction in perplexity by 4.81 on WikiText2 and 3.46 on PTB, while also decreasing memory usage by 52.6%. Besides, LoRAPrune also matches semi-structural pruning across multiple LLMs, proving its wide applicability. The code is available at https://github.com/aim-uofa/LoRAPrune.

Mingyang Zhang, Jing Liu, Ganggui Ding et al.

Lately, the practice of utilizing task-specific fine-tuning has been implemented to improve the performance of large language models (LLM) in subsequent tasks. Through the integration of diverse LLMs, the overall competency of LLMs is significantly boosted. Nevertheless, traditional ensemble methods are notably memory-intensive, necessitating the simultaneous loading of all specialized models into GPU memory. To address the inefficiency, model merging strategies have emerged, merging all LLMs into one model to reduce the memory footprint during inference. Despite these advances, model merging often leads to parameter conflicts and performance decline as the number of experts increases. Previous methods to mitigate these conflicts include post-pruning and partial merging. However, both approaches have limitations, particularly in terms of performance and storage efficiency when merged experts increase. To address these challenges, we introduce Channel Merging, a novel strategy designed to minimize parameter conflicts while enhancing storage efficiency. This method clusters and merges channel parameters based on their similarity to form several groups offline. By ensuring that only highly similar parameters are merged within each group, it significantly reduces parameter conflicts. During inference, we can instantly look up the expert parameters from the merged groups, preserving specialized knowledge. Our experiments demonstrate that Channel Merging consistently delivers high performance, matching unmerged models in tasks like English and Chinese reasoning, mathematical reasoning, and code generation. Moreover, it obtains results comparable to model ensemble with just 53% parameters when used with a task-specific router.

Wancai Zheng, Linlin Ou, Jiajie He et al.

Recent 3D Gaussian Splatting (3DGS) techniques for Visual Simultaneous Localization and Mapping (SLAM) have significantly progressed in tracking and high-fidelity mapping. However, their sequential optimization framework and sensitivity to dynamic objects limit real-time performance and robustness in real-world scenarios. We present UP-SLAM, a real-time RGB-D SLAM system for dynamic environments that decouples tracking and mapping through a parallelized framework. A probabilistic octree is employed to manage Gaussian primitives adaptively, enabling efficient initialization and pruning without hand-crafted thresholds. To robustly filter dynamic regions during tracking, we propose a training-free uncertainty estimator that fuses multi-modal residuals to estimate per-pixel motion uncertainty, achieving open-set dynamic object handling without reliance on semantic labels. Furthermore, a temporal encoder is designed to enhance rendering quality. Concurrently, low-dimensional features are efficiently transformed via a shallow multilayer perceptron to construct DINO features, which are then employed to enrich the Gaussian field and improve the robustness of uncertainty prediction. Extensive experiments on multiple challenging datasets suggest that UP-SLAM outperforms state-of-the-art methods in both localization accuracy (by 59.8%) and rendering quality (by 4.57 dB PSNR), while maintaining real-time performance and producing reusable, artifact-free static maps in dynamic environments.The project: https://aczheng-cai.github.io/up_slam.github.io/

Xinyi Yu, Siyu Xu, Yuehai Fan et al.

To solve the coupling problem of control loops and the adaptive parameter tuning problem in the multi-input multi-output (MIMO) PID control system, a self-adaptive LSAC-PID algorithm is proposed based on deep reinforcement learning (RL) and Lyapunov-based reward shaping in this paper. For complex and unknown mobile robot control environment, an RL-based MIMO PID hybrid control strategy is firstly presented. According to the dynamic information and environmental feedback of the mobile robot, the RL agent can output the optimal MIMO PID parameters in real time, without knowing mathematical model and decoupling multiple control loops. Then, to improve the convergence speed of RL and the stability of mobile robots, a Lyapunov-based reward shaping soft actor-critic (LSAC) algorithm is proposed based on Lyapunov theory and potential-based reward shaping method. The convergence and optimality of the algorithm are proved in terms of the policy evaluation and improvement step of soft policy iteration. In addition, for line-following robots, the region growing method is improved to adapt to the influence of forks and environmental interference. Through comparison, test and cross-validation, the simulation and real-environment experimental results all show good performance of the proposed LSAC-PID tuning algorithm.

Xinyi Yu, Yuehai Fan, Siyu Xu et al.

Proportional-integral-derivative (PID) control is the most widely used in industrial control, robot control and other fields. However, traditional PID control is not competent when the system cannot be accurately modeled and the operating environment is variable in real time. To tackle these problems, we propose a self-adaptive model-free SAC-PID control approach based on reinforcement learning for automatic control of mobile robots. A new hierarchical structure is developed, which includes the upper controller based on soft actor-critic (SAC), one of the most competitive continuous control algorithms, and the lower controller based on incremental PID controller. Soft actor-critic receives the dynamic information of the mobile robot as input, and simultaneously outputs the optimal parameters of incremental PID controllers to compensate for the error between the path and the mobile robot in real time. In addition, the combination of 24-neighborhood method and polynomial fitting is developed to improve the adaptability of SAC-PID control method to complex environments. The effectiveness of the SAC-PID control method is verified with several different difficulty paths both on Gazebo and real mecanum mobile robot. Futhermore, compared with fuzzy PID control, the SAC-PID method has merits of strong robustness, generalization and real-time performance.