Publications (26)
PUGS: Zero-shot Physical Understanding with Gaussian Splatting
Yinghao Shuai, Ran Yu, Yuantao Chen +9
Current robotic systems can understand the categories and poses of objects well. But understanding physical properties like mass, friction, and hardness, in the wild, remains chall…
Growing from Exploration: A self-exploring framework for robots based on foundation models
Shoujie Li, Ran Yu, Tong Wu +3
Intelligent robot is the ultimate goal in the robotics field. Existing works leverage learning-based or optimization-based methods to accomplish human-defined tasks. However, the c…
WorldKG: A World-Scale Geographic Knowledge Graph
Alishiba Dsouza, Nicolas Tempelmeier, Ran Yu +2
OpenStreetMap is a rich source of openly available geographic information. However, the representation of geographic entities, e.g., buildings, mountains, and cities, within OpenSt…
Depth Restoration of Hand-Held Transparent Objects for Human-to-Robot Handover
Ran Yu, Haixin Yu, Shoujie Li +3
Transparent objects are common in daily life, while their optical properties pose challenges for RGB-D cameras to capture accurate depth information. This issue is further amplifie…
Predicting Knowledge Gain during Web Search based on Multimedia Resource Consumption
Christian Otto, Ran Yu, Georg Pardi +7
In informal learning scenarios the popularity of multimedia content, such as video tutorials or lectures, has significantly increased. Yet, the users' interactions, navigation beha…
Real-time Human-Centric Segmentation for Complex Video Scenes
Ran Yu, Chenyu Tian, Weihao Xia +3
Most existing video tasks related to "human" focus on the segmentation of salient humans, ignoring the unspecified others in the video. Few studies have focused on segmenting and t…
A Survey of Reinforcement Learning-Based Motion Planning for Autonomous Driving: Lessons Learned from a Driving Task Perspective
Zhuoren Li, Guizhe Jin, Ran Yu +8
Reinforcement learning (RL), with its ability to explore and optimize policies in complex, dynamic decision-making tasks, has emerged as a promising approach to addressing motion p…
HCRMP: A LLM-Hinted Contextual Reinforcement Learning Framework for Autonomous Driving
Zhiwen Chen, Bo Leng, Zhuoren Li +4
Integrating Large Language Models (LLMs) with Reinforcement Learning (RL) can enhance autonomous driving (AD) performance in complex scenarios. However, current LLM-Dominated RL me…
Risk-Aware Reinforcement Learning for Autonomous Driving: Improving Safety When Driving through Intersection
Bo Leng, Ran Yu, Wei Han +3
Applying reinforcement learning to autonomous driving has garnered widespread attention. However, classical reinforcement learning methods optimize policies by maximizing expected…
Detecting, Understanding and Supporting Everyday Learning in Web Search
Ran Yu, Ujwal Gadiraju, Stefan Dietze
Web search is among the most ubiquitous online activities, commonly used to acquire new knowledge and to satisfy learning-related objectives through informational search sessions.…
Multi-Timescale Hierarchical Reinforcement Learning for Unified Behavior and Control of Autonomous Driving
Guizhe Jin, Zhuoren Li, Bo Leng +3
Reinforcement Learning (RL) is increasingly used in autonomous driving (AD) and shows clear advantages. However, most RL-based AD methods overlook policy structure design. An RL po…
PoseDet: Fast Multi-Person Pose Estimation Using Pose Embedding
Chenyu Tian, Ran Yu, Xinyuan Zhao +3
Current methods of multi-person pose estimation typically treat the localization and the association of body joints separately. It is convenient but inefficient, leading to additio…
ECHO: An Open Research Platform for Evaluation of Chat, Human Behavior, and Outcomes
Jiqun Liu, Nischal Dinesh, Ran Yu
ECHO (Evaluation of Chat, Human behavior, and Outcomes) is an open research platform designed to support reproducible, mixed-method studies of human interaction with both conversat…
Learning Quality-aware Dynamic Memory for Video Object Segmentation
Yong Liu, Ran Yu, Fei Yin +4
Recently, several spatial-temporal memory-based methods have verified that storing intermediate frames and their masks as memory are helpful to segment target objects in videos. Ho…
A Research Vision for Web Search on Emerging Topics
Alisa Rieger, Stefan Dietze, Ran Yu
We regularly encounter information on novel, emerging topics for which the body of knowledge is still evolving, which can be linked, for instance, to current events. A primary way…
Global Spectral Filter Memory Network for Video Object Segmentation
Yong Liu, Ran Yu, Jiahao Wang +4
This paper studies semi-supervised video object segmentation through boosting intra-frame interaction. Recent memory network-based methods focus on exploiting inter-frame temporal…
Uncertainty-Aware Safety-Critical Decision and Control for Autonomous Vehicles at Unsignalized Intersections
Ran Yu, Zhuoren Li, Lu Xiong +2
Reinforcement learning (RL) has demonstrated potential in autonomous driving (AD) decision tasks. However, applying RL to urban AD, particularly in intersection scenarios, still fa…
Creating Knowledge Graphs for Geographic Data on the Web
Elena Demidova, Alishiba Dsouza, Simon Gottschalk +2
Geographic data plays an essential role in various Web, Semantic Web and machine learning applications. OpenStreetMap and knowledge graphs are critical complementary sources of geo…
Predicting User Knowledge Gain in Informational Search Sessions
Ran Yu, Ujwal Gadiraju, Peter Holtz +3
Web search is frequently used by people to acquire new knowledge and to satisfy learning-related objectives. In this context, informational search missions with an intention to obt…
FeaXDrive: Feasibility-aware Trajectory-Centric Diffusion Planning for End-to-End Autonomous Driving
Baoyun Wang, Zhuoren Li, Ran Yu +6
End-to-end diffusion planning has shown strong potential for autonomous driving, but the physical feasibility of generated trajectories remains insufficiently addressed. In particu…
Expert Knowledge-driven Reinforcement Learning for Autonomous Racing via Trajectory Guidance and Dynamics Constraints
Bo Leng, Weiqi Zhang, Zhuoren Li +4
The paper introduces TraD‑RL, a reinforcement‑learning framework for autonomous racing that uses expert racing lines for state augmentation and reward shaping, and incorporates veh…
SaL-Lightning Dataset: Search and Eye Gaze Behavior, Resource Interactions and Knowledge Gain during Web Search
Christian Otto, Markus Rokicki, Georg Pardi +9
The emerging research field Search as Learning investigates how the Web facilitates learning through modern information retrieval systems. SAL research requires significant amounts…
Utilizing Large Language Models for Named Entity Recognition in Traditional Chinese Medicine against COVID-19 Literature: Comparative Study
Xu Tong, Nina Smirnova, Sharmila Upadhyaya +5
Objective: To explore and compare the performance of ChatGPT and other state-of-the-art LLMs on domain-specific NER tasks covering different entity types and domains in TCM against…
Still Haven't Found What You're Looking For -- Detecting the Intent of Web Search Missions from User Interaction Features
Ran Yu, Limock, Stefan Dietze
Web search is among the most frequent online activities. Whereas traditional information retrieval techniques focus on the information need behind a user query, previous work has s…
SATac: A Thermoluminescence Enabled Tactile Sensor for Concurrent Perception of Temperature, Pressure, and Shear
Ziwu Song, Ran Yu, Xuan Zhang +5
Most vision-based tactile sensors use elastomer deformation to infer tactile information, which can not sense some modalities, like temperature. As an important part of human tacti…
TweetsCOV19 -- A Knowledge Base of Semantically Annotated Tweets about the COVID-19 Pandemic
Dimitar Dimitrov, Erdal Baran, Pavlos Fafalios +4
Publicly available social media archives facilitate research in the social sciences and provide corpora for training and testing a wide range of machine learning and natural langua…