Search Results for author:
Found 112 papers, 42 papers with code
Variational PatchMatch MultiView Reconstruction and Refinement
We formulate the combined multi-view stereo reconstruction and refinement as a variational optimization problem.
Deep Anticipation: Light Weight Intelligent Mobile Sensing in IoT by Recurrent Architecture
However, the mobile sensing perception brings new challenges for how to efficiently analyze and intelligently interpret the deluge of IoT data in mission- critical services.
Towards Robotic Eye Surgery: Marker-free, Online Hand-eye Calibration using Optical Coherence Tomography Images
Ophthalmic microsurgery is known to be a challenging operation, which requires very precise and dexterous manipulation.
Guessing Smart: Biased Sampling for Efficient Black-Box Adversarial Attacks
We consider adversarial examples for image classification in the black-box decision-based setting.
Graph Neural Networks for Modelling Traffic Participant Interaction
We show that prediction error in scenarios with much interaction decreases by 30% compared to a model that does not take interactions into account.
What the Constant Velocity Model Can Teach Us About Pedestrian Motion Prediction
Our work shows how neural networks for pedestrian motion prediction can be thoroughly evaluated and our results indicate which research directions for neural motion prediction are promising in future.
A Novel Method for the Absolute Pose Problem with Pairwise Constraints
In this paper, we consider pairwise constraints and propose a globally optimal algorithm for solving the absolute pose estimation problem.
Targetless Rotational Auto-Calibration of Radar and Camera for Intelligent Transportation Systems
Most intelligent transportation systems use a combination of radar sensors and cameras for robust vehicle perception.
Globally optimal vertical direction estimation in Atlanta World
Accordingly, we propose a vertical direction estimation method by considering the relationship between the vertical frame and horizontal frames.
Leveraging Semantic Embeddings for Safety-Critical Applications
Semantic Embeddings are a popular way to represent knowledge in the field of zero-shot learning.
Copy and Paste: A Simple But Effective Initialization Method for Black-Box Adversarial Attacks
Many optimization methods for generating black-box adversarial examples have been proposed, but the aspect of initializing said optimizers has not been considered in much detail.
Providentia -- A Large-Scale Sensor System for the Assistance of Autonomous Vehicles and Its Evaluation
An Intelligent Infrastructure System can fill in the gaps in a vehicle's perception and extend its field of view by providing additional detailed information about its surroundings, in the form of a digital model of the current traffic situation, i. e. a digital twin.
Identity Recognition in Intelligent Cars with Behavioral Data and LSTM-ResNet Classifier
Identity recognition in a car cabin is a critical task nowadays and offers a great field of applications ranging from personalizing intelligent cars to suit drivers physical and behavioral needs to increasing safety and security.
Indirect and Direct Training of Spiking Neural Networks for End-to-End Control of a Lane-Keeping Vehicle
Building spiking neural networks (SNNs) based on biological synaptic plasticities holds a promising potential for accomplishing fast and energy-efficient computing, which is beneficial to mobile robotic applications.
Task-Independent Spiking Central Pattern Generator: A Learning-Based Approach
This model is the main focus of this work, as its contribution is not limited to engineering but also applicable to neuroscience.
Counterfactual Policy Evaluation for Decision-Making in Autonomous Driving
If a policy can handle all counterfactual worlds well, it either has seen similar situations during training or it generalizes well and is deemed to be fit enough to be executed in the actual world.
Graph Neural Networks and Reinforcement Learning for Behavior Generation in Semantic Environments
We show that graph neural networks are capable of handling scenarios with a varying number and order of vehicles during training and application.
AerialMPTNet: Multi-Pedestrian Tracking in Aerial Imagery Using Temporal and Graphical Features
Due to the challenges such as the large number and the tiny size of the pedestrians (e. g., 4 x 4 pixels) with their similar appearances as well as different scales and atmospheric conditions of the images with their extremely low frame rates (e. g., 2 fps), current state-of-the-art algorithms including the deep learning-based ones are unable to perform well.
Formalizing Traffic Rules for Machine Interpretability
We contribute a formalized set of traffic rules for single-direction carriageways, such as on highways.
Robotics
Complex Robotic Manipulation via Graph-Based Hindsight Goal Generation
In this paper, we propose graph-based hindsight goal generation (G-HGG), an extension of HGG selecting hindsight goals based on shortest distances in an obstacle-avoiding graph, which is a discrete representation of the environment.
Neuron Activation Analysis for Multi-Joint Robot Reinforcement Learning
We analyze the individual neuron activity distribution in the network, introduce a pruning algorithm to reduce network size keeping the performance, and with these dense network representations we spot correlations of neuron activity patterns among networks trained for robot manipulators with different joint number.
RSKDD-Net: Random Sample-based Keypoint Detector and Descriptor
To tackle the information loss of random sampling, we exploit a novel random dilation cluster strategy to enlarge the receptive field of each sampled point and an attention mechanism to aggregate the positions and features of neighbor points.
LAP-Net: Adaptive Features Sampling via Learning Action Progression for Online Action Detection
At each time step, this sampling strategy first estimates current action progression and then decide what temporal ranges should be used to aggregate the optimal supplementary features.
PointINet: Point Cloud Frame Interpolation Network
Generally, the frame rates of mechanical LiDAR sensors are 10 to 20 Hz, which is much lower than other commonly used sensors like cameras.
A Spiking Central Pattern Generator for the control of a simulated lamprey robot running on SpiNNaker and Loihi neuromorphic boards
In this work we propose a spiking CPG neural network and its implementation on neuromorphic hardware as a means to control a simulated lamprey model.
Lightweight Convolutional Neural Network with Gaussian-based Grasping Representation for Robotic Grasping Detection
Extensive experiments on two public grasping datasets, Cornell and Jacquard demonstrate the state-of-the-art performance of our method in balancing accuracy and inference speed.
Ranked #1 on
Robotic Grasping
on Jacquard dataset
Experience-Based Heuristic Search: Robust Motion Planning with Deep Q-Learning
With Deep Reinforcement Learning, optimal driving strategies for such problems can be derived also for higher-dimensional problems.
Addressing Inherent Uncertainty: Risk-Sensitive Behavior Generation for Automated Driving using Distributional Reinforcement Learning
Specifically, we first learn an optimal policy in an uncertain environment with Deep Distributional Reinforcement Learning.
Distributional Reinforcement Learning
Reinforcement Learning (RL)
Risk-Constrained Interactive Safety under Behavior Uncertainty for Autonomous Driving
In this work, we adopt this safety objective for interactive planning.
NAST: Non-Autoregressive Spatial-Temporal Transformer for Time Series Forecasting
Although Transformer has made breakthrough success in widespread domains especially in Natural Language Processing (NLP), applying it to time series forecasting is still a great challenge.
FloMo: Tractable Motion Prediction with Normalizing Flows
In our work, we model motion prediction directly as a density estimation problem with a normalizing flow between a noise distribution and the future motion distribution.
Non-Holonomic RRT & MPC: Path and Trajectory Planning for an Autonomous Cycle Rickshaw
Therefore, the algorithm presented in this paper needs to anticipate and avoid dynamic obstacles, such as pedestrians or bicycles, but also be fast enough in order to work in real-time so that it can adapt to changes in the environment.
Motion Planning
Trajectory Planning
Robotics
ACM-Net: Action Context Modeling Network for Weakly-Supervised Temporal Action Localization
Traditional methods mainly focus on foreground and background frames separation with only a single attention branch and class activation sequence.
Ranked #5 on
Weakly Supervised Action Localization
on THUMOS14
Weakly Supervised Action Localization
Weakly-supervised Temporal Action Localization
+1
A Hierarchical State-Machine-Based Framework for Platoon Manoeuvre Descriptions
This paper introduces the SEAD framework that simplifies the process of designing and describing autonomous vehicle platooning manoeuvres.
Temp-Frustum Net: 3D Object Detection with Temporal Fusion
Furthermore, ablation studies reinforce that the subject of improvement is temporal fusion and show the effects of different placements of TFM in the object detection pipeline.
3D Human Pose Regression using Graph Convolutional Network
We propose one such graph convolutional network named PoseGraphNet for 3D human pose regression from 2D poses.
Ranked #201 on
3D Human Pose Estimation
on Human3.6M
Safety Metrics for Semantic Segmentation in Autonomous Driving
Within the context of autonomous driving, safety-related metrics for deep neural networks have been widely studied for image classification and object detection.
Meta-Reinforcement Learning in Broad and Non-Parametric Environments
Recent state-of-the-art artificial agents lack the ability to adapt rapidly to new tasks, as they are trained exclusively for specific objectives and require massive amounts of interaction to learn new skills.
Vogtareuth Rehab Depth Datasets: Benchmark for Marker-less Posture Estimation in Rehabilitation
We evaluate it on our rehab datasets, and observe that the performance degrades significantly from non-rehab to rehab, highlighting the need for these datasets.
Towards Cognitive Navigation: Design and Implementation of a Biologically Inspired Head Direction Cell Network
As a vital cognitive function of animals, the navigation skill is first built on the accurate perception of the directional heading in the environment.
Multi-Agent Constrained Policy Optimisation
To fill these gaps, in this work, we formulate the safe MARL problem as a constrained Markov game and solve it with policy optimisation methods.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Comparing Heuristics, Constraint Optimization, and Reinforcement Learning for an Industrial 2D Packing Problem
Cutting and Packing problems are occurring in different industries with a direct impact on the revenue of businesses.
TridentAdapt: Learning Domain-invariance via Source-Target Confrontation and Self-induced Cross-domain Augmentation
Due to the difficulty of obtaining ground-truth labels, learning from virtual-world datasets is of great interest for real-world applications like semantic segmentation.
Evaluating Muscle Synergies with EMG Data and Physics Simulation in the Neurorobotics Platform
We use our framework to analyze raw EMG data collected during an isometric knee extension study to identify synergies that drive a musculoskeletal lower limb model.
Are Transformers More Robust? Towards Exact Robustness Verification for Transformers
As an emerging type of Neural Networks (NNs), Transformers are used in many domains ranging from Natural Language Processing to Autonomous Driving.
Time-coded Spiking Fourier Transform in Neuromorphic Hardware
After several decades of continuously optimizing computing systems, the Moore's law is reaching itsend.
Graph Neural Networks for Relational Inductive Bias in Vision-based Deep Reinforcement Learning of Robot Control
We derive a graph representation that models the physical structure of the manipulator and combines the robot's internal state with a low-dimensional description of the visual scene generated by an image encoding network.
Real-Time and Robust 3D Object Detection Within Road-Side LiDARs Using Domain Adaptation
This work aims to address the challenges in domain adaptation of 3D object detection using infrastructure LiDARs.
A Survey of Robust 3D Object Detection Methods in Point Clouds
The purpose of this work is to review the state-of-the-art LiDAR-based 3D object detection methods, datasets, and challenges.
Federated Learning Framework Coping with Hierarchical Heterogeneity in Cooperative ITS
Considering the individual heterogeneity of data distribution, computational and communication capabilities across traffic agents and roadside units, we employ a novel method that addresses the heterogeneity of different aggregation layers of the framework architecture, i. e., aggregation in layers of roadside units and cloud.
A9-Dataset: Multi-Sensor Infrastructure-Based Dataset for Mobility Research
As part of the first set of data, which we describe in this paper, we provide camera and LiDAR frames from two overhead gantry bridges on the A9 autobahn with the corresponding objects labeled with 3D bounding boxes.
3D Object Detection with a Self-supervised Lidar Scene Flow Backbone
Our main contribution leverages learned flow and motion representations and combines a self-supervised backbone with a supervised 3D detection head.
A Review of Safe Reinforcement Learning: Methods, Theory and Applications
To establish a good foundation for future research in this thread, in this paper, we provide a review for safe RL from the perspectives of methods, theory and applications.
Analysis of Randomization Effects on Sim2Real Transfer in Reinforcement Learning for Robotic Manipulation Tasks
Fully randomized simulations and fine-tuning show differentiated results and translate better to the real robot than the other approaches tested.
Edge-Aided Sensor Data Sharing in Vehicular Communication Networks
Specifically, when the measurement error from the sensors (also referred as measurement noise) is unknown and time varying, the performance of the data fusion process is restricted, which represents a major challenge in the calibration of sensors.
Accurate and Real-time Pseudo Lidar Detection: Is Stereo Neural Network Really Necessary?
In the experiments, we develop a system with a less powerful stereo matching predictor and adopt the proposed refinement schemes to improve the accuracy.
Federated Learning via Decentralized Dataset Distillation in Resource-Constrained Edge Environments
In federated learning, all networked clients contribute to the model training cooperatively.
Hardware faults that matter: Understanding and Estimating the safety impact of hardware faults on object detection DNNs
The evaluation of several representative object detection models shows that even a single bit flip can lead to a severe silent data corruption event with potentially critical safety implications, with e. g., up to (much greater than) 100 FPs generated, or up to approx.
Improving the Safety of 3D Object Detectors in Autonomous Driving using IoGT and Distance Measures
State-of-the-art object detectors are commonly evaluated based on accuracy metrics such as mean Average Precision (mAP).
Learning from Symmetry: Meta-Reinforcement Learning with Symmetrical Behaviors and Language Instructions
We propose a dual-MDP meta-reinforcement learning method that enables learning new tasks efficiently with symmetrical behaviors and language instructions.
LoopDA: Constructing Self-loops to Adapt Nighttime Semantic Segmentation
In this paper, we propose LoopDA for domain adaptive nighttime semantic segmentation.
ResFed: Communication Efficient Federated Learning by Transmitting Deep Compressed Residuals
To address this bottleneck, we introduce a residual-based federated learning framework (ResFed), where residuals rather than model parameters are transmitted in communication networks for training.
Autonomous Driving Simulator based on Neurorobotics Platform
There are many artificial intelligence algorithms for autonomous driving, but directly installing these algorithms on vehicles is unrealistic and expensive.
Focal Network for Image Restoration
Image restoration aims to reconstruct a sharp image from its degraded counterpart, which plays an important role in many fields.
Ranked #7 on
Image Dehazing
on SOTS Outdoor
Attention Mechanism for Contrastive Learning in GAN-based Image-to-Image Translation
Using real road testing to optimize autonomous driving algorithms is time-consuming and capital-intensive.
A Human-Centered Safe Robot Reinforcement Learning Framework with Interactive Behaviors
Deployment of Reinforcement Learning (RL) algorithms for robotics applications in the real world requires ensuring the safety of the robot and its environment.
BCSSN: Bi-direction Compact Spatial Separable Network for Collision Avoidance in Autonomous Driving
In this paper, we propose a CNN-based method that overcomes the limitation by establishing feature correlations between regions in sequential images using variants of attention.
Sequential Spatial Network for Collision Avoidance in Autonomous Driving
Several autonomous driving strategies have been applied to autonomous vehicles, especially in the collision avoidance area.
Fast and Accurate Object Detection on Asymmetrical Receptive Field
To address the above challenges, based on extensive literature research, this paper analyzes methods for improving and optimizing mainstream object detection algorithms from the perspective of evolution of one-stage and two-stage object detection algorithms.
TMA: Temporal Motion Aggregation for Event-based Optical Flow
In this paper, we argue that temporal continuity is a vital element of event-based optical flow and propose a novel Temporal Motion Aggregation (TMA) approach to unlock its potential.
UMC: A Unified Bandwidth-efficient and Multi-resolution based Collaborative Perception Framework
To verify our algorithm, we conducted experiments on the V2X-Sim and OPV2V datasets.
FedBEVT: Federated Learning Bird's Eye View Perception Transformer in Road Traffic Systems
Our findings suggest that FedBEVT outperforms the baseline approaches in all four use cases, demonstrating the potential of our approach for improving BEV perception in autonomous driving.
DiGA: Distil to Generalize and then Adapt for Domain Adaptive Semantic Segmentation
Domain adaptive semantic segmentation methods commonly utilize stage-wise training, consisting of a warm-up and a self-training stage.
Selective Frequency Network for Image Restoration
Image restoration aims to reconstruct the latent sharp image from its corrupted counterpart.
Ranked #1 on
Deblurring
on RSBlur
Occlusion Robust 3D Human Pose Estimation with StridedPoseGraphFormer and Data Augmentation
We show that our proposed method compares favorably with the state-of-the-art (SoA).
IRNeXt: Rethinking Convolutional Network Design for Image Restoration
We present IRNeXt, a simple yet effective convolutional network architecture for image restoration.
Ranked #4 on
Image Dehazing
on SOTS Outdoor
Meta-Reinforcement Learning Based on Self-Supervised Task Representation Learning
On MuJoCo and Meta-World benchmarks, MoSS outperforms prior works in terms of asymptotic performance, sample efficiency (3-50x faster), adaptation efficiency, and generalization robustness on broad and diverse task distributions.
Efficient and Deterministic Search Strategy Based on Residual Projections for Point Cloud Registration
Estimating the rigid transformation between two LiDAR scans through putative 3D correspondences is a typical point cloud registration paradigm.
V2X-Boosted Federated Learning for Cooperative Intelligent Transportation Systems with Contextual Client Selection
Machine learning (ML) has revolutionized transportation systems, enabling autonomous driving and smart traffic services.
DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encoder
Generative model-based deep clustering frameworks excel in classifying complex data, but are limited in handling dynamic and complex features because they require prior knowledge of the number of clusters.
Towards Cognitive Bots: Architectural Research Challenges
Software bots operating in multiple virtual digital platforms must understand the platforms' affordances and behave like human users.
Language-Conditioned Imitation Learning with Base Skill Priors under Unstructured Data
In this evaluation, we set up ten tasks and achieved an average 30% improvement in our approach compared to the current state-of-the-art approach, demonstrating a high generalization capability in both simulated environments and the real world.
DiAReL: Reinforcement Learning with Disturbance Awareness for Robust Sim2Real Policy Transfer in Robot Control
We introduce a disturbance-augmented Markov decision process in delayed settings as a novel representation to incorporate disturbance estimation in training on-policy reinforcement learning algorithms.
Strip Attention for Image Restoration
As a long-standing task, image restoration aims to recover the latent sharp image from its degraded counterpart.
Ranked #6 on
Image Dehazing
on SOTS Outdoor
PoseGraphNet++: Enriching 3D Human Pose with Orientation Estimation
Existing kinematic skeleton-based 3D human pose estimation methods only predict joint positions.
BEA: Revisiting anchor-based object detection DNN using Budding Ensemble Architecture
The proposed loss functions in BEA improve the confidence score calibration and lower the uncertainty error, which results in a better distinction of true and false positives and, eventually, higher accuracy of the object detection models.
Representation Abstractions as Incentives for Reinforcement Learning Agents: A Robotic Grasping Case Study
The results show that RL agents using numerical states can perform on par with non-learning baselines.
Integrate-and-fire circuit for converting analog signals to spikes using phase encoding
Thus, we provide an end-to-end neuromorphic application that generates the frequency spectrum of an electric signal without the need for an ADC or a digital signal processing algorithm.
YOLO-BEV: Generating Bird's-Eye View in the Same Way as 2D Object Detection
Vehicle perception systems strive to achieve comprehensive and rapid visual interpretation of their surroundings for improved safety and navigation.
Transformation Decoupling Strategy based on Screw Theory for Deterministic Point Cloud Registration with Gravity Prior
This paper focuses on addressing the robust correspondence-based registration problem with gravity prior that often arises in practice.
Image Restoration via Frequency Selection
Image restoration aims to reconstruct the latent sharp image from its corrupted counterpart.
Ranked #2 on
Image Dehazing
on SOTS Outdoor
User-Like Bots for Cognitive Automation: A Survey
In this survey, we aim to explore the role of cognitive architectures in supporting efforts towards engineering software bots with advanced general intelligence.
VLTSeg: Simple Transfer of CLIP-Based Vision-Language Representations for Domain Generalized Semantic Segmentation
We thus propose a new vision-language approach for domain generalized segmentation, which improves the domain generalization SOTA by 7. 6% mIoU when training on the synthetic GTA5 dataset.
Ranked #1 on
Semantic Segmentation
on Cityscapes test
(using extra training data)
Contact Energy Based Hindsight Experience Prioritization
Multi-goal robot manipulation tasks with sparse rewards are difficult for reinforcement learning (RL) algorithms due to the inefficiency in collecting successful experiences.
Exploring the potential of channel interactions for image restoration
Image restoration aims to reconstruct a clear image from a degraded observation.
Ranked #1 on
Image Dehazing
on SOTS Outdoor
GarchingSim: An Autonomous Driving Simulator with Photorealistic Scenes and Minimalist Workflow
However, the availability of free and open-source simulators is limited, and the installation and configuration process can be daunting for beginners and interdisciplinary researchers.
ControlUDA: Controllable Diffusion-assisted Unsupervised Domain Adaptation for Cross-Weather Semantic Segmentation
Data generation is recognized as a potent strategy for unsupervised domain adaptation (UDA) pertaining semantic segmentation in adverse weathers.
Collaborative Semantic Occupancy Prediction with Hybrid Feature Fusion in Connected Automated Vehicles
Additionally, due to the lack of a collaborative perception dataset designed for semantic occupancy prediction, we augment a current collaborative perception dataset to include 3D collaborative semantic occupancy labels for a more robust evaluation.
Path Planning based on 2D Object Bounding-box
The implementation of Autonomous Driving (AD) technologies within urban environments presents significant challenges.
Online Efficient Safety-Critical Control for Mobile Robots in Unknown Dynamic Multi-Obstacle Environments
This paper proposes a LiDAR-based goal-seeking and exploration framework, addressing the efficiency of online obstacle avoidance in unstructured environments populated with static and moving obstacles.
PCDepth: Pattern-based Complementary Learning for Monocular Depth Estimation by Best of Both Worlds
Therefore, existing complementary learning approaches for MDE fuse intensity information from images and scene details from event data for better scene understanding.
Real-Time Adaptive Safety-Critical Control with Gaussian Processes in High-Order Uncertain Models
Subsequently, the hyperparameters of the Gaussian model are trained with a specially compound kernel, and the Gaussian model's online inferential capability and computational efficiency are strengthened by updating a solitary inducing point derived from new samples, in conjunction with the learned hyperparameters.
Dual-domain strip attention for image restoration
In this paper, we develop a dual-domain strip attention mechanism for image restoration by enhancing representation learning, which consists of spatial and frequency strip attention units.
Ranked #5 on
Image Dehazing
on SOTS Outdoor
LEAD: Learning Decomposition for Source-free Universal Domain Adaptation
Besides, LEAD is also appealing in that it is complementary to most existing methods.
Ranked #1 on
Universal Domain Adaptation
on VisDA2017
MAP: MAsk-Pruning for Source-Free Model Intellectual Property Protection
In this paper, we target a practical setting where only a well-trained source model is available and investigate how we can realize IP protection.
TeaMs-RL: Teaching LLMs to Teach Themselves Better Instructions via Reinforcement Learning
The development of Large Language Models (LLMs) often confronts challenges stemming from the heavy reliance on human annotators in the reinforcement learning with human feedback (RLHF) framework, or the frequent and costly external queries tied to the self-instruct paradigm.
EC-IoU: Orienting Safety for Object Detectors via Ego-Centric Intersection-over-Union
This paper presents safety-oriented object detection via a novel Ego-Centric Intersection-over-Union (EC-IoU) measure, addressing practical concerns when applying state-of-the-art learning-based perception models in safety-critical domains such as autonomous driving.
Towards Single-System Illusion in Software-Defined Vehicles -- Automated, AI-Powered Workflow
We propose a novel model- and feature-based approach to development of vehicle software systems, where the end architecture is not explicitly defined.
AdaIR: Adaptive All-in-One Image Restoration via Frequency Mining and Modulation
Our approach is motivated by the observation that different degradation types impact the image content on different frequency subbands, thereby requiring different treatments for each restoration task.
Omni-Kernel Network for Image Restoration
Extensive experiments demonstrate that our network achieves state-of-the-art performance on 11 benchmark datasets for three representative image restoration tasks, including image dehazing, image desnowing, and image defocus deblurring.
Ranked #8 on
Image Dehazing
on SOTS Outdoor
Residual Chain Prediction for Autonomous Driving Path Planning
Our findings highlight the potential of Residual Chain Loss to revolutionize planning component of autonomous driving systems, marking a significant step forward in the quest for level 5 autonomous driving system.
Synergy of Large Language Model and Model Driven Engineering for Automated Development of Centralized Vehicular Systems
We present a prototype of a tool leveraging the synergy of model driven engineering (MDE) and Large Language Models (LLM) for the purpose of software development process automation in the automotive industry.
