A5064076235- Robot Manipulation and Learning
- Motor Control and Adaptation
- Software Engineering Research
- Reinforcement Learning in Robotics
- Data Visualization and Analytics
- Interactive and Immersive Displays
- Innovative Human-Technology Interaction
- Augmented Reality Applications
- Robotic Locomotion and Control
- Topic Modeling
- Image Retrieval and Classification Techniques
- Muscle activation and electromyography studies
- Robotics and Sensor-Based Localization
- Multimodal Machine Learning Applications
- Context-Aware Activity Recognition Systems
- Speech and dialogue systems
- Human-Automation Interaction and Safety
- Personal Information Management and User Behavior
- Video Analysis and Summarization
- Robotics and Automated Systems
Google (United States)
2019-2024
Urbana University
2004
Carnegie Mellon University
2003
Intelligent manipulation benefits from the capacity to flexibly control an end-effector with high degrees of freedom (DoF) and dynamically react environment. However, due challenges collecting effective training data learning efficiently, most grasping algorithms today are limited top-down movements open-loop execution. In this work, we propose a new low-cost hardware interface for demonstrations by people in diverse environments. This makes it possible train robust end-to-end 6DoF...
A person seeking someone else's attention is normally able to quickly assess how interruptible they are. This assessment allows for behavior we perceive as natural, socially appropriate, or simply polite. On the other hand, today's computer systems are almost entirely oblivious human world operate in, and typically have no way take into account interruptibility of user. paper presents a Wizard Oz study exploring whether, how, robust sensor-based predictions might be constructed, which...
There is no such thing as a disembodied mind. We posit that cognitive development can only occur through interaction with the physical world. To this end, we are developing robotic platform for purpose of studying cognition. suggest central component cognition memory which primarily associative, one where learning occurs correlation events from diverse inputs. also human-like requires well-integrated sensory-motor system, to provide these As implemented in our robot, system includes binaural...
Visual programming provides beginner-level programmers with a coding-free experience to build their customized pipelines. Existing systems require users pipeline entirely from scratch, implying that novice need set up and link appropriate nodes all by themselves, starting blank workspace. We present InstructPipe, an AI assistant enables start prototyping machine learning (ML) pipelines text instructions. designed two LLM modules code interpreter execute our solution. generate pseudocode of...
Foundational multi-modal models have democratized AI access, yet the construction of complex, customizable machine learning pipelines by novice users remains a grand challenge. This paper demonstrates visual programming system that allows novices to rapidly prototype multimodal pipelines. We first conducted formative study with 58 contributors and collected 236 proposals served various practical needs. then distilled our findings into design matrix primitive nodes for prototyping pipelines,...
Intelligent manipulation benefits from the capacity to flexibly control an end-effector with high degrees of freedom (DoF) and dynamically react environment. However, due challenges collecting effective training data learning efficiently, most grasping algorithms today are limited top-down movements open-loop execution. In this work, we propose a new low-cost hardware interface for demonstrations by people in diverse environments. Leveraging data, show that it is possible train robust...
Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile grasping) actions: pushing can help rearrange cluttered objects to make space for arms fingers; likewise, grasping displace movements more precise collision-free. In this work, we demonstrate that it is possible discover learn these scratch through model-free deep reinforcement learning. Our method involves training two fully convolutional networks map visual observations one...