检索结果-内蒙古大学图书馆

FSDP: Fast and Safe Data-Driven Overtaking Trajectory Planning for Head-to-Head Autonomous Racing Competitions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Hu, Cheng Huang, Jihao Mao, Wule Fu, Yonghao Chi, Xuemin Qin, Haotong Baumann, Nicolas Liu, Zhitao Magno, Michele Xie, Lei Department of Control Science and Engineering Zhejiang University China Center for Project-Based Learning D-ITET ETH Zurich Switzerland

(Image Present) Generating overtaking trajectories in autonomous racing is a challenging task, as the trajectory must satisfy the vehicle’s dynamics and ensure safety and real-time performance running on resource-constrained hardware. This work proposes the Fast and Safe Data-Driven Planner to address this challenge. Sparse Gaussian predictions are introduced to improve both the computational efficiency and accuracy of opponent predictions. Furthermore, the proposed approach employs a bi-level quadratic programming framework to generate an overtaking trajectory leveraging the opponent predictions. The first level uses polynomial fitting to generate a rough trajectory, from which reference states and control inputs are derived for the second level. The second level formulates a model predictive control optimization problem in the Frenet frame, generating a trajectory that satisfies both kinematic feasibility and safety. Experimental results on the F1TENTH platform show that our method outperforms the State-of-the-Art, achieving an 8.93% higher overtaking success rate, allowing the maximum opponent speed, ensuring a smoother ego trajectory, and reducing 74.04% computational time compared to the Predictive Spliner method. The code is available at: https://***/ZJU-DDRX/ FSDP. Copyright © 2025, The Authors. All rights reserved.

关键词： Quadratic programming

Enhancing Autonomous Driving Systems with On-Board Deployed Large Language Models

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Baumann, Nicolas Hu, Cheng Sivasothilingam, Paviththiren Qin, Haotong Xie, Lei Magno, Michele Benini, Luca Center for Project-Based Learning ETH Zurich Switzerland Integrated Systems Laboratory ETH Zurich Switzerland Department of Control Science and Engineering Zhejiang University China

Neural Networks (NNs) trained through supervised learning, struggle with managing edge-case scenarios common in real-world driving due to the intractability of exhaustive datasets covering all edge-cases, making knowledge-driven approaches, akin to how humans intuitively detect unexpected driving behavior, a suitable complement to data-driven methods. This work proposes a hybrid architecture combining low-level Model Predictive Controller (MPC) with locally deployed Large Language Models (LLMs) to enhance decision-making and Human Machine Interaction (HMI). The DecisionxLLM module evaluates robotic state information against natural language instructions to ensure adherence to desired driving behavior. The MPCxLLM module then adjusts MPC parameters based on LLM-generated insights, achieving control adaptability while preserving the safety and constraint guarantees of traditional MPC systems. Further, to enable efficient on-board deployment and to eliminate dependency on cloud connectivity, we shift processing to the on-board computing platform: We propose an approach that exploits Retrieval Augmented Generation (RAG), Low Rank Adaptation (LoRA) fine-tuning, and quantization. Experimental results demonstrate that these enhancements yield significant improvements in reasoning accuracy by up to 10.45%, control adaptability by as much as 52.2%, and up to 10.5× increase in computational efficiency (tokens/s), validating the proposed framework’s practicality for real-time deployment even on down-scaled robotic platforms. This work bridges high-level decision-making with low-level control adaptability, offering a synergistic framework for knowledge-driven and adaptive Autonomous Driving Systems (ADS). © 2025, CC BY.

关键词： Predictive control systems

GP-enhanced Autonomous Drifting Framework using ADMM-based iLQR

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Xie, Yangyang Hu, Cheng Baumann, Nicolas Ghignone, Edoardo Magno, Michele Xie, Lei State Key Laboratory of Industrial Control Technology Zhejiang University Zhejiang Hangzhou310027 China Center for Project-Based Learning D-ITET ETH Zurich Switzerland

Autonomous drifting is a complex challenge due to the highly nonlinear dynamics and the need for precise real-time control, especially in uncertain environments. To address these limitations, this paper presents a hierarchical control framework for autonomous vehicles drifting along general paths, primarily focusing on addressing model inaccuracies and mitigating computational challenges in real-time control. The framework integrates Gaussian Process (GP) regression with an Alternating Direction Method of Multipliers (ADMM)-based iterative Linear Quadratic Regulator (iLQR). GP regression effectively compensates for model residuals, improving accuracy in dynamic conditions. ADMM-based iLQR not only combines the rapid trajectory optimization of iLQR but also utilizes ADMM’s strength in decomposing the problem into simpler sub-problems. Simulation results demonstrate the effectiveness of the proposed framework, with significant improvements in both drift trajectory tracking and computational efficiency. Our approach resulted in a 38% reduction in RMSE lateral error and achieved an average computation time that is 75% lower than that of the Interior Point OPTimizer (IPOPT). © 2025, CC BY.

关键词：

RLPP: A Residual Method for Zero-Shot Real-World Autonomous Racing on Scaled Platforms

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Ghignone, Edoardo Baumann, Nicolas Hu, Cheng Wang, Jonathan Xie, Lei Carron, Andrea Magno, Michele Center for Project-Based Learning D-ITET ETH Zurich Switzerland Department of Control Science and Engineering Zhejiang University China Institute for Dynamic Systems and Control D-MAVT ETH Zürich Switzerland

Autonomous racing presents a complex environment requiring robust controllers capable of making rapid decisions under dynamic conditions. While traditional controllers based on tire models are reliable, they often demand extensive tuning or system identification. Reinforcement learning (RL) methods offer significant potential due to their ability to learn directly from interaction, yet they typically suffer from the Simto-Real gap, where policies trained in simulation fail to perform effectively in the real world. In this paper, we propose RLPP, a residual RL framework that enhances a Pure Pursuit (PP) controller with an RL-based residual. This hybrid approach leverages the reliability and interpretability of PP while using RL to fine-tune the controller’s performance in real-world scenarios. Extensive testing on the F1TENTH platform demonstrates that RLPP improves lap times of the baseline controllers by up to 6.37 %, closing the gap to the State-of-the-Art (SotA) methods by more than 52 % and providing reliable performance in zero-shot real-world deployment, overcoming key challenges associated with the Sim-to-Real transfer and reducing the performance gap from simulation to reality by more than 8-fold when compared to the baseline RL controller. The RLPP framework is made available as an open-source tool, encouraging further exploration and advancement in autonomous racing research. The code is available at: ***/forzaeth/*** Codes 68T40 © 2025, CC BY.

关键词： Reinforcement learning

TinycenterSpeed: Efficient center-based Object Detection for Autonomous Racing

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Reichlin, Neil Baumann, Nicolas Ghignone, Edoardo Magno, Michele Center for Project-based Learning D-ITET ETH Zurich Switzerland

Perception within autonomous driving is nearly synonymous with Neural Networks (NNs). Yet, the domain of autonomous racing is often characterized by scaled, computationally limited robots used for cost-effectiveness and safety. For this reason, opponent detection and tracking systems typically resort to traditional computer vision techniques due to computational constraints. This paper introduces TinycenterSpeed, a streamlined adaptation of the seminal centerPoint method, optimized for real-time performance on 1:10 scale autonomous racing platforms. This adaptation is viable even on OBCs powered solely by Central Processing Units (CPUs), as it incorporates the use of an external Tensor Processing Unit (TPU). We demonstrate that, compared to Adaptive Breakpoint Detector (ABD), the current State-of-the-Art (SotA) in scaled autonomous racing, TinycenterSpeed not only improves detection and velocity estimation by up to 61.38% but also supports multi-opponent detection and estimation. It achieves real-time performance with an inference time of just 7.88 ms on the TPU, significantly reducing CPU utilization 8.3-fold. © 2025, CC BY.

关键词： Object detection

LEDNet: a multimodal foundation model for robust deepfake detection

学校读者我要写书评

暂无评论

SCIENCE CHINA Information Sciences 2025年第6期68卷

作者： Renshuai TAO Shijie TANG Haotong QIN Wei WANG Yunchao WEI Yao ZHAO Institute of Information Science Beijing Jiaotong University Beijing 100044 China Center for Project-Based Learning (PBL) D-ITET ETH Zürich 8092 Switzerland

The proliferation of artificial intelligence (AI)-generated content on social media has escalated concerns regarding misinformation, privacy, and security. Current deepfake detection methods struggle to generalize effectively, failing to keep pace with evolving generative models like generative adversarial networks (GANs) and diffusion models. Inspired by the robustness of “real" and “fake" descriptions in the language world, in this paper, we introduce the language-enhanced deepfake detection network (LEDNet), a multimodal foundation model that leverages both linguistic and visual information to improve detection accuracy and adaptability. We are the first to exploit multi-modal technologies for generalized deepfake detection through an un-trained-backbonemechanism, which utilizes pre-trained vision-language models without the need for additional retraining. The model is powered by two key components: language-guided knowledge aggregation (LKA), which assembles a linguistic knowledge base of real and fake indicators, and attention-based vision-language mutualism (AVM), which aligns multimodal features to enhance detection precision. Extensive experiments across 25 popular deepfake datasets demonstrate that LEDNet outperforms state-of-the-art methods, achieving superior accuracy and generalization across diverse deepfake generation techniques. This work sets a new benchmark in multimodal deepfake detection, advancing the application of foundation models in this domain.

关键词： computer vision multimodel foundation model deepfake detection

TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Object Detection Network for Low Power Microcontrollers 5

学校读者我要写书评

暂无评论

TinyissimoYOLO: A Quantized, Low-Memory Footprint, TinyML Ob...

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Moosmann, Julian Giordano, Marco Vogt, Christian Magno, Michele Center for Project Based Learning - Eth Zürich Switzerland

ISBN: (纸本)9798350332674

This paper introduces a highly flexible, quantized, memory-efficient, and ultra-lightweight object detection network, called TinyissimoYOLO. It aims to enable object detection on microcontrollers in the power domain of milliwatts, with less than 0.5 MB memory available for storing convolutional neural network (CNN) weights. The proposed quantized network architecture with 422 k parameters, enables real-time object detection on embedded microcontrollers, and it has been evaluated to exploit CNN accelerators. In particular, the proposed network has been deployed on the MAX78000 microcontroller achieving high frame-rate of up to 180 fps and an ultra-low energy consumption of only 196 μJ per inference with an inference efficiency of more than 106 MAC/Cycle. TinyissimoYOLO can be trained for any multi-object detection. However, considering the small network size, adding object detection classes will increase the size and memory consumption of the network, thus object detection with up to 3 classes is demonstrated. Furthermore, the network is trained using quantization-aware training and deployed with 8-bit quantization on different microcontrollers, such as STM32H7A3, STM32L4R9, Apollo4b and on the MAX78000's CNN accelerator. Performance evaluations are presented in this paper. © 2023 IEEE.

关键词： Microcontrollers

How theater can promote inclusive engineering campuses 125

学校读者我要写书评

暂无评论

How theater can promote inclusive engineering campuses

125th ASEE Annual Conference and Exposition

作者： Di Biasio, David Boudreau, Kristin Quinn, Paula Worcester Polytechnic Institute Center for Project-Based Learning United States

How can the arts contribute to a culture of inclusivity within engineering? This paper explores preliminary findings from our study of Worcester Polytechnic Institute (WPI), a four-year, primarily engineering college whose longtime undergraduate curriculum requires all students to complete a substantial humanities project. Many engineering students at WPI choose to do this humanities work in theatre, where they study classic and contemporary plays and participate in productions. They have the option of writing an original play as their capstone project, and if successful their play may be staged for a campus audience. For 35 years, an original short play festival on this campus has performed the work of students. From nearly the beginning, these original plays featured the difficult themes of sexual identity and orientation. In 2017, to celebrate this rich heritage, the theatre program presented a retrospective of LGBTQ+ themed plays written and performed by students since 1987. We report here on our findings from a mixed-method study of this theatre program and its influence on the culture at WPI. While in general, engineering culture is not a welcoming place for LGBTQ+ people or for open discussions about non-normative sexuality, the data we have collected around WPIs theatre program present a powerful exception to that rule. Our data set includes the scripts of 22 student- or alumni-authored plays on LGBTQ+ themes, a survey of 80 audience members at the 35-year retrospective of LGBTQ+ themed plays, and interviews with people associated with the theatre program, including its faculty director and several openly queer engineering students and alumni. Together, these documents make a compelling case that theatre can contribute to an engineering culture that is more than typically inclusive of non-normative sexualities (not just for people involved with the theatre program but for the educational culture at large). Because our study subjects are engineering majors, n

关键词：

KP2Dtiny: Quantized Neural Keypoint Detection and Description on the Edge 5

学校读者我要写书评

暂无评论

KP2Dtiny: Quantized Neural Keypoint Detection and Descriptio...

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Ruegg, Thomas Giordano, Marco Magno, Michele D-ITET Eth Zurich Zurich Switzerland Eth Zurich Center for Project Based Learning Zurich Switzerland

ISBN: (纸本)9798350332674

Detection and description of keypoints in images is a fundamental component of a wide range of tasks such as Simultaneous Localization And Mapping (SLAM), image alignment and structure from motion (SfM). Efficient computation of these features is crucial for real-time applications and has been addressed by multiple handcrafted algorithms and, recently, by deep neural network-based detectors. Learned detectors achieve high detection performance, but pose high computational requirements, making them slow and impractical for low-power resource constraint platforms. This paper presents a quantized neural keypoint detector and descriptor optimized for edge devices exploiting two recent AI platforms such as MAX78000 by Analog Devices and the Coral AI USB accelerator from Google. To accommodate the diverse constraints and requirements of various applications, we propose and evaluate two model architectures (KP2DtinySmall and KP2DtinyFast) and deploy them on the aforementioned platforms using full 8-bit integer quantization. Furthermore, we extensively evaluate these models in terms of power, latency and accuracy, reporting results on three image sizes (88x88, 320x240 and 640x480), evaluating both quantized and non-quantized models. Fully quantized, KP2DtinySmall reduces network size by a factor of 54x while improving homographic estimation accuracy on 88x88 images on the most stringent threshold (Correctness d1) by 32.4% (0.550) and on 320x240 images by 10.7% (0.648) compared to the KeypointNet architecture by Yang You et. al. This result is achieved by designing a new network with low power platforms in mind, particularly addressing the lower resolution by increasing the density of detectable features. Deployed on the MAX78000 MCU, inference of low-resolution images is run at 59 FPS, consuming 1.1 mJ per image. On the Coral usb accelerator, KP2DtinyFast runs inference on low-resolution images at 527 FPS consuming 3.1 mJ, on high resolution it achieves 70 FPS at 19.9 mJ pe

关键词： Deep neural networks