检索结果-内蒙古大学图书馆

International Symposium on Low Power Electronics and Design (ISLPED)

作者： Vahidreza Moghaddas Hammam Kattan Tim Bücher Mikail Yayla Jian-Jia Chen Hussam Amrouch TU Dortmund University University of Stuttgart Lamarr Institute for Machine Learning and Artificial Intelligences AI Processor Design Technical University of Munich Munich Institute of Robotics and Machine Intelligence

Neural processing units (NPUs) have become indispensable for meeting the high computational demands of deep neural networks (DNNs). They provide a very efficient solution, thanks to having a huge MAC array that enables massive parallelism. Nevertheless, such an architecture exhibits excessive on-chip power densities leading to a localized hot-spot that seriously heats its surroundings. This work demonstrates how the on-chip temperatures induced by the MAC array create a spatial thermal gradient through the on-chip SRAM memory. This makes the memory regions sensitive to different error probabilities (Perror), leading to significant accuracy drops when DNNs are being executed. To surmount this challenge, we employ on-chip superlattice thermoelectric (TEC) cooling devices that effectively reduce the memory temperature. Although scaling the memory voltage makes SRAM cells more sensitive to errors, it significantly decreases the leakage power, which compensates for the power consumed by the incorporated TEC devices. Furthermore, operating the SRAM at a lower voltage and temperature substantially increases its lifetime because voltage and temperature are key stimuli of transistor aging. By running multi-physics simulations using commercial finite-element tools and SPICE simulations for the 14nm FinFET technology, we accurately derive the relation between the Perror in different memory regions and the corresponding cooling cost. We then propose a three-stage temperature-aware layer-wise memory mapping that exploits different degrees of the sensitivity of NN layers to errors towards maximizing the DNN accuracy while minimizing the cooling cost. Experimental results reveal that our method notably improves the DNN accuracy compared to existing temperature-oblivious memory mapping.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Safe Multi-Agent Reinforcement learning for Behavior-Based Cooperative Navigation

arXiv

引用

arXiv 2023年

作者： Dawood, Murad Pan, Sicong Dengler, Nils Zhou, Siqi Schoellig, Angela P. Bennewitz, Maren The Humanoid Robots Lab University of Bonn Germany The Lamarr Institute for Machine Learning and Artificial Intelligence and the Center for Robotics Bonn Germany The Learning Systems and Robotics lab The Technical University of Munich Germany

In this paper, we address the problem of behavior-based cooperative navigation of mobile robots using safe multi-agent reinforcement learning (MARL). Our work is the first to focus on cooperative navigation without individual reference targets for the robots, using a single target for the formation's centroid. This eliminates the complexities involved in having several path planners to control a team of robots. To ensure safety, our MARL framework uses model predictive control (MPC) to prevent actions that could lead to collisions during training and execution. We demonstrate the effectiveness of our method in simulation and on real robots, achieving safe behavior-based cooperative navigation without using individual reference targets, with zero collisions, and faster target reaching compared to baselines. Finally, we study the impact of MPC safety filters on the learning process, revealing that we achieve faster convergence during training and we show that our approach can be safely deployed on real robots, even during early stages of the training. © 2023, CC0.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Sustainable Grid through Distributed Data Centers Spinning AI Demand for Grid Stabilization and Optimization

arXiv

引用

arXiv 2025年

作者： Evans, Scott C. Dahlin, Nathan Ndiaye, Ibrahima Ekanayake, Sachini Piyoni Duncan, Alexander Rose, Blake Huang, Hao AI-Machine Learning Robotics Lab United States Electrification Mission United States ECE Department University at Albany SUNY United States

We propose a disruptive paradigm to actively place and schedule TWhrs of parallel AI jobs strategically on the grid, at distributed, grid-aware high performance compute data centers (HPC) capable of using their massive power and energy load to stabilize the grid while reducing grid build-out requirements, maximizing use of renewable energy, and reducing Green House Gas (GHG) emissions. Our approach will enable the creation of new, value adding markets for spinning compute demand, providing market based incentives that will drive the joint optimization of energy and learning. © 2025, CC BY.

关键词： Stabilization

来源：评论

学校读者我要写书评

暂无评论

SimpleMapping: Real-Time Visual-Inertial Dense Mapping with Deep Multi-View Stereo

SimpleMapping: Real-Time Visual-Inertial Dense Mapping with ...

引用

International Symposium on Mixed and Augmented Reality (ISMAR)

作者： Yingye Xin Xingxing Zuo Dongyue Lu Stefan Leutenegger Smart Robotics Lab Technical University of Munich Germany Munich Center for Machine Learning (MCML) Germany

We present a real-time visual-inertial dense mapping method capable of performing incremental 3D mesh reconstruction with high quality using only sequential monocular images and inertial measurement unit (IMU) readings. 6-DoF camera poses are estimated by a robust feature-based visual-inertial odometry (VIO), which also generates noisy sparse 3D map points as a by-product. We propose a sparse point aided multi-view stereo neural network (SPA-MVSNet) that can effectively leverage the informative but noisy sparse points from the VIO system. The sparse depth from VIO is firstly completed by a single-view depth completion network. This dense depth map, although naturally limited in accuracy, is then used as a prior to guide our MVS network in the cost volume generation and regularization for accurate dense depth prediction. Predicted depth maps of keyframe images by the MVS network are incrementally fused into a global map using TSDF-Fusion. We extensively evaluate both the proposed SPA-MVSNet and the entire dense mapping system on several public datasets as well as our own dataset, demonstrating the system’s impressive generalization capabilities and its ability to deliver high-quality 3D reconstruction online. Our proposed dense mapping system achieves a 39.7% improvement in F-score over existing systems when evaluated on the challenging scenarios of the EuRoC dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Control-Barrier-Aided Teleoperation with Visual-Inertial SLAM for Safe MAV Navigation in Complex Environments

Control-Barrier-Aided Teleoperation with Visual-Inertial SLA...

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Siqi Zhou Sotiris Papatheodorou Stefan Leutenegger Angela P. Schoellig Learning Systems and Robotics Lab School of Computation Information and Technology Technical University of Munich Munich Institute of Robotics and Machine Intelligence (MIRMI) Smart Robotics Lab School of Computation Information and Technology Technical University of Munich Department of Computing Smart Robotics Lab Imperial College London

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

In this paper, we consider a Micro Aerial Vehicle (MAV) system teleoperated by a non-expert and introduce a perceptive safety filter that leverages Control Barrier Functions (CBFs) in conjunction with Visual-Inertial Simultaneous Localization and Mapping (VI-SLAM) and dense 3D occupancy mapping to guarantee safe navigation in complex and unstructured environments. Our system relies solely on onboard IMU measurements, stereo infrared images, and depth images and autonomously corrects teleoperated inputs when they are deemed unsafe. We define a point in 3D space as unsafe if it satisfies either of two conditions: (i) it is occupied by an obstacle, or (ii) it remains unmapped. At each time step, an occupancy map of the environment is updated by the VI-SLAM by fusing the onboard measurements, and a CBF is constructed to parameterize the (un)safe region in the 3D space. Given the CBF and state feedback from the VI-SLAM module, a safety filter computes a certified reference that best matches the teleoperation input while satisfying the safety constraint encoded by the CBF. In contrast to existing perception-based safe control frameworks, we directly close the perception-action loop and demonstrate the full capability of safe control in combination with real-time VI-SLAM without any external infrastructure or prior knowledge of the environment. We verify the efficacy of the perceptive safety filter in real-time MAV experiments using exclusively onboard sensing and computation and show that the teleoperated MAV is able to safely navigate through unknown environments despite arbitrary inputs sent by the teleoperator.

关键词： Teleoperators State feedback Three-dimensional displays Simultaneous localization and mapping Navigation Real-time systems Time measurement

来源：评论

学校读者我要写书评

暂无评论

Latent Action Priors for Locomotion with Deep Reinforcement learning

arXiv

引用

arXiv 2024年

作者： Hausdörfer, Oliver von Rohr, Alexander Lefort, Éric Schoellig, Angela P. The Technical University of Munich Germany TUM School of Computation Information and Technology Department of Computer Engineering Learning Systems and Robotics Lab Germany Munich Institute of Robotics and Machine Intelligence Germany

Deep Reinforcement learning (DRL) enables robots to learn complex behaviors through interaction with the environment. However, due to the unrestricted nature of the learning algorithms, the resulting solutions are often brittle and appear unnatural. This is especially true for learning direct joint-level torque control, as inductive biases are difficult to integrate into the learning process. We propose an inductive bias for learning locomotion that is especially useful for torque control: latent actions learned from a small dataset of expert demonstrations. This prior allows the policy to directly leverage knowledge contained in the expert’s actions and facilitates more efficient exploration. We observe that the agent is not restricted to the reward levels of the demonstration, and performance in transfer tasks is improved significantly. Latent action priors combined with style rewards for imitation leads to a closer replication of the expert’s behavior. Videos and code are available at https://***/view/ latent-action-priors. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Relative Representations: Topological and Geometric Perspectives

arXiv

引用

arXiv 2024年

作者： García-Castellanos, Alejandro Marchetti, Giovanni Luca Kragic, Danica Scolamiero, Martina Amsterdam Machine Learning Lab University of Amsterdam Netherlands Department of Mathematics KTH Royal Institute of Technology Sweden Division of Robotics Perception and Learning KTH Royal Institute of Technology Sweden

Relative representations are an established approach to zero-shot model stitching, consisting of a non-trainable transformation of the latent space of a deep neural network. Based on insights of topological and geometric nature, we propose two improvements to relative representations. First, we introduce a normalization procedure in the relative transformation, resulting in invariance to non-isotropic rescalings and permutations. The latter coincides with the symmetries in parameter space induced by common activation functions. Second, we propose to deploy topological densification when fine-tuning relative representations, a topological regularization loss encouraging clustering within classes. We provide an empirical investigation on a natural language task, where both the proposed variations yield improved performance on zero-shot model stitching. © 2024, CC BY.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

Multi-Step Model Predictive Safety Filters: Reducing Chattering by Increasing the Prediction Horizon

Multi-Step Model Predictive Safety Filters: Reducing Chatter...

引用

IEEE Conference on Decision and Control

作者： Federico Pizarro Bejarano Lukas Brunke Angela P. Schoellig the Learning Systems and Robotics Lab University of Toronto Robotics Institute and the Vector Institute for Artificial Intelligence Toronto Canada Technical University of Munich and the Munich Institute for Robotics and Machine Intelligence (MIRMI) Germany

learning-based controllers have demonstrated su-perior performance compared to classical controllers in various tasks. However, providing safety guarantees is not trivial. Safety, the satisfaction of state and input constraints, can be guaranteed by augmenting the learned control policy with a safety filter. Model predictive safety filters (MPSFs) are a common safety filtering approach based on model predictive control (MPC). MPSFs seek to guarantee safety while minimizing the difference between the proposed and applied inputs in the immediate next time step. This limited foresight can lead to jerky motions and undesired oscillations close to constraint boundaries, known as chattering. In this paper, we reduce chattering by considering input corrections over a longer horizon. Under the assumption of bounded model uncertainties, we prove recursive feasibility using techniques from robust MPC. We verified the proposed approach in both extensive simulation and quadrotor exper-iments. In experiments with a Crazyflie 2.0 drone, we show that, in addition to preserving the desired safety guarantees, the proposed MPSF reduces chattering by more than a factor of 4 compared to previous MPSF formulations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Radar-Only Odometry and Mapping for Autonomous Vehicles

Radar-Only Odometry and Mapping for Autonomous Vehicles

引用

IEEE International Conference on robotics and Automation (ICRA)

作者： Daniel Casado Herraez Matthias Zeller Le Chang Ignacio Vizzo Michael Heidingsfeld Cyrill Stachniss CARIAD SE and With the University of Bonn Germany CARIAD SE and With the University of Stuttgart Germany Dexory UK University of Bonn is With CARIAD SE Germany Center for Robotics University of Bonn and With the Lamarr Institute for Machine Learning and Artificial Intelligence Germany

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Odometry and mapping play a pivotal role in the navigation of autonomous vehicles. In this paper, we address the problem of pose estimation and map creation using only radar sensors. We focus on two odometry estimation approaches followed by a mapping step. The first one is a new point-to-point ICP approach that leverages the velocity information provided by 3D radar sensors. The second one is advantageous for 2D radars with a low number of samples, and particularly useful for scenarios where the sensor is being blocked by large dynamic obstacles. It exploits a constant velocity filter and the measured Doppler velocities to estimate the vehicle’s ego-motion. We enrich this with a filtering step to improve the accuracy of the points in the resulting map. We put our work to the test using the View of Delft and NuScenes datasets, which involve 3D and 2D radar sensors. Our findings illustrate state-of-the-art performance of our odometry techniques in terms of accuracy when compared to existing alternatives. Moreover, we demonstrate that our map filtering methodology achieves higher similarity rates than the raw unfiltered map when benchmarked against a corresponding LiDAR map.

关键词： Three-dimensional displays Accuracy Laser radar Radar measurements Navigation Doppler radar Sensors

来源：评论

学校读者我要写书评

暂无评论

Balanced resonate-and-fire neurons 24

Balanced resonate-and-fire neurons

引用

Proceedings of the 41st International Conference on machine learning

作者： Saya Higuchi Sebastian Kairat Sander M. Bohté Sebastian Otte Adaptive AI Lab Institute of Robotics and Cognitive Systems University of Lübeck Germany Machine Learning Group Centrum Wiskunde & Informatica (CWI) Amsterdam The Netherlands

The resonate-and-fire (RF) neuron, introduced over two decades ago, is a simple, efficient, yet biologically plausible spiking neuron model, which can extract frequency patterns within the time domain due to its resonating membrane dynamics. However, previous RF formulations suffer from intrinsic shortcomings that limit effective learning and prevent exploiting the principled advantage of RF neurons. Here, we introduce the balanced RF (BRF) neuron, which alleviates some of the intrinsic limitations of vanilla RF neurons and demonstrates its effectiveness within recurrent spiking neural networks (RSNNs) on various sequence learning tasks. We show that networks of BRF neurons achieve overall higher task performance, produce only a fraction of the spikes, and require significantly fewer parameters as compared to modern RSNNs. Moreover, BRF-RSNN consistently provide much faster and more stable training convergence, even when bridging many hundreds of time steps during backpropagation through time (BPTT). These results underscore that our BRF-RSNN is a strong candidate for future large-scale RSNN architectures, further lines of research in SNN methodology, and more efficient hardware implementations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：