Johnny Chung Lee
I joined Google in 2011, and I am currently an Engineering Director in the AR/XR team focused on multi-modal AI systems for wearable devices, such as Project Astra. My areas of interest include machine learning, computer vision, sensors, robotics, and human-computer interaction. In my career, I've had the opportunity to work on the following projects:
- Founded a program in the Google Research/Deepmind Robotics program focusing on teleoperation and learning from human demonstrations. The team developed a production operational micro-fulfillment warehouse using robotic arms for pick & pack from an automatic storage and retrieval system (ASRS).
- Founded and lead Google Tango in 2013, a mobile computer vision effort to bring 6-DOF tracking and 3D sensing to mobile phones, tablets, and headsets. This included the development and launch of multiple mobile phones incorporating 3D sensing and tracking. The technology from Tango has become ARCore for Android enabling mobile AR applications running on billions of phones, and the Visual Positioning Service for Google Maps Geospatial API enabling global scale precision location and immersive content.
- Lead the software team that developed 6-DOF tracking for Daydream VR headsets and future XR hardware.
- Oversaw some hardware R&D efforts for VR/AR technologies, including novel tracking technologies, headset prototypes, optical technologies, and sensing algorithms.
- As a part of Google X, I made early contributions to Google Glass, Loon, and other non-public projects.
- Prior to Google, I developed human tracking algorithms for the Xbox 360 Kinect at Microsoft.
- Personal projects have included low-cost interactive whiteboards and desktop VR displays using the Nintendo Wii remote, which have received over 15 million views, performed as a TED talk in 2008, and recognized by MIT Technology Review's TR35.
Authored Publications
Sort By
Augmented Object Intelligence with XR-Objects
Mustafa Doga Dogan
Karan Ahuja
Andrea Colaco
Proceedings of the 37th Annual ACM Symposium on User Interface Software and Technology (UIST), ACM (2024), pp. 1-15
Preview abstract
Seamless integration of physical objects as interactive digital entities remains a challenge for spatial computing. This paper explores Augmented Object Intelligence (AOI) in the context of XR, an interaction paradigm that aims to blur the lines between digital and physical by equipping real-world objects with the ability to interact as if they were digital, where every object has the potential to serve as a portal to digital functionalities. Our approach utilizes real-time object segmentation and classification, combined with the power of Multimodal Large Language Models (MLLMs), to facilitate these interactions without the need for object pre-registration. We implement the AOI concept in the form of XR-Objects, an open-source prototype system that provides a platform for users to engage with their physical environment in contextually relevant ways using object-based context menus. This system enables analog objects to not only convey information but also to initiate digital actions, such as querying for details or executing tasks. Our contributions are threefold: (1) we define the AOI concept and detail its advantages over traditional AI assistants, (2) detail the XR-Objects system’s open-source design and implementation, and (3) show its versatility through various use cases and a user study.
View details
Experiencing InstructPipe: Building Multi-modal AI Pipelines via Prompting LLMs and Visual Programming
Zhongyi Zhou
Jing Jin
Xiuxiu Yuan
Jun Jiang
Jingtao Zhou
Yiyi Huang
Kristen Wright
Jason Mayes
Mark Sherwood
Ram Iyengar
Na Li
Extended Abstracts of the 2024 CHI Conference on Human Factors in Computing Systems, ACM, pp. 5
Preview abstract
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 a visual programming system that allows novices to rapidly prototype multimodal AI pipelines. We first conducted a formative study with 58 contributors and collected 236 proposals of multimodal AI pipelines that served various practical needs. We then distilled our findings into a design matrix of primitive nodes for prototyping multimodal AI visual programming pipelines, and implemented a system with 65 nodes. To support users' rapid prototyping experience, we built InstructPipe, an AI assistant based on large language models (LLMs) that allows users to generate a pipeline by writing text-based instructions. We believe InstructPipe enhances novice users onboarding experience of visual programming and the controllability of LLMs by offering non-experts a platform to easily update the generation.
View details
InstructPipe: Building Visual Programming Pipelines with Human Instructions
Zhongyi Zhou
Jing Jin
Xiuxiu Yuan
Jun Jiang
Jingtao Zhou
Yiyi Huang
Kristen Wright
Jason Mayes
Mark Sherwood
Ram Iyengar
Na Li
arXiv, 2312.09672 (2023)
Preview abstract
Visual programming provides beginner-level programmers with a coding-free experience to build their customized pipelines. Existing systems require users to build a pipeline entirely from scratch, implying that novice users need to set up and link appropriate nodes all by themselves, starting from a blank workspace. We present InstructPipe, an AI assistant that enables users to start prototyping machine learning (ML) pipelines with text instructions. We designed two LLM modules and a code interpreter to execute our solution. LLM modules generate pseudocode of a target pipeline, and the interpreter renders a pipeline in the node-graph editor for further human-AI collaboration. Technical evaluations reveal that InstructPipe reduces user interactions by 81.1% compared to traditional methods. Our user study (N=16) showed that InstructPipe empowers novice users to streamline their workflow in creating desired ML pipelines, reduce their learning curve, and spark innovative ideas with open-ended commands.
View details
Learning to Fold Real Garments with One Arm: A Case Study in Cloud-Based Robotics Research
Ryan Hoque
Kaushik Shivakumar
Shrey Aeron
Gabriel Deza
Aditya Ganapathi
Andy Zeng
Ken Goldberg
IEEE International Conference on Intelligent Robots and Systems (IROS) (2022) (to appear)
Preview abstract
Autonomous fabric manipulation is a longstanding challenge in robotics, but evaluating progress is difficult due to the cost and diversity of robot hardware. Using Reach, a new cloud robotics platform that enables low-latency remote execution of control policies on physical robots, we present the first systematic benchmarking of fabric manipulation algorithms on physical hardware. We develop 4 novel learning-based algorithms that model expert actions, keypoints, reward functions, and dynamic motions, and we compare these against 4 learning-free and inverse dynamics algorithms on the task of folding a crumpled T-shirt with a single robot arm. The entire lifecycle of data collection, model training, and policy evaluation is performed remotely without physical access to the robot workcell. Results suggest a new algorithm combining imitation learning with analytic methods achieves 84% of human-level performance on the folding task.
View details
Socratic Models: Composing Zero-Shot Multimodal Reasoning with Language
Andy Zeng
Brian Ichter
Stefan Welker
Aveek Purohit
Michael Ryoo
Pete Florence
arXiv (2022)
Preview abstract
Large pretrained (e.g., "foundation") models exhibit distinct capabilities depending on the domain of data they are trained on. While these domains are generic, they may only barely overlap. For example, visual-language models (VLMs) are trained on Internet-scale image captions, but large language models (LMs) are further trained on Internet-scale text with no images (e.g., spreadsheets, SAT questions, code). As a result, these models store different forms of commonsense knowledge across different domains. In this work, we show that this diversity is symbiotic, and can be leveraged through Socratic Models (SMs): a modular framework in which multiple pretrained models may be composed zero-shot i.e., via multimodal-informed prompting, to exchange information with each other and capture new multimodal capabilities, without requiring finetuning. With minimal engineering, SMs are not only competitive with state-of-the-art zero-shot image captioning and video-to-text retrieval, but also enable new applications such as (i) answering free-form questions about egocentric video, (ii) engaging in multimodal assistive dialogue with people (e.g., for cooking recipes) by interfacing with external APIs and databases (e.g., web search), and (iii) robot perception and planning. Prototypes are available at socraticmodels.github.io
View details
Implicit Behavioral Cloning
Pete Florence
Corey Lynch
Andy Zeng
Oscar Ramirez
Laura Downs
Igor Mordatch
CoRL (2021)
Preview abstract
We find that across a wide range of robot policy learning scenarios, treating supervised policy learning with an implicit model generally performs better, on average, than commonly used explicit models. We present extensive experiments on this finding, and we provide both intuitive insight and theoretical arguments distinguishing the properties of implicit models compared to their explicit counterparts, particularly with respect to approximating complex, potentially discontinuous and multi-valued (set-valued) functions. On robotic policy learning tasks we show that implicit behavioral cloning policies with energy-based models (EBM) often outperform common explicit (Mean Square Error, or Mixture Density) behavioral cloning policies, including on tasks with high-dimensional action spaces and visual image inputs. We find these policies provide competitive results or outperform state-of-the-art offline reinforcement learning methods on the challenging human-expert tasks from the D4RL benchmark suite, despite using no reward information. In the real world, robots with implicit policies can learn complex and remarkably subtle behaviors on contact-rich tasks from human demonstrations, including tasks with high combinatorial complexity and tasks requiring 1mm precision.
View details
Transporter Networks: Rearranging the Visual World for Robotic Manipulation
Andy Zeng
Pete Florence
Stefan Welker
Jonathan Chien
Travis Armstrong
Ivan Krasin
Dan Duong
Conference on Robot Learning (CoRL) (2020)
Preview abstract
Robotic manipulation can be formulated as inducing a sequence of spatial displacements: where the space being moved can encompass object(s) or an end effector. In this work, we propose the Transporter Network, a simple model architecture that rearranges deep features to infer spatial displacements from visual input -- which can parameterize robot actions. It makes no assumptions of objectness (e.g. canonical poses, models, or keypoints), it exploits spatial symmetries, and is orders of magnitude more sample efficient than our benchmarked alternatives in learning vision-based manipulation tasks: from stacking a pyramid of blocks, to assembling kits with unseen objects; from manipulating deformable ropes, to pushing piles of small objects with closed-loop feedback. Our method can represent complex multi-modal policy distributions and generalizes to multi-step sequential tasks, as well as 6DoF pick-and-place. Experiments on 10 simulated tasks show that it learns faster and generalizes better than a variety of end-to-end baselines, including policies that use ground-truth object poses. We validate our methods with hardware in the real world.
View details
Spatial Action Maps for Mobile Manipulation
Jimmy Wu
Xingyuan Sun
Andy Zeng
Shuran Song
Szymon Rusinkiewicz
Robotics: Science and Systems (RSS) (2020)
Preview abstract
Typical end-to-end formulations for learning robotic navigation involve predicting a small set of steering command actions (e.g., step forward, turn left, turn right, etc.) from images of the current state (e.g., a bird's-eye view of a SLAM reconstruction). Instead, we show that it can be advantageous to learn with dense action representations defined in the same domain as the state. In this work, we present "spatial action maps," in which the set of possible actions is represented by a pixel map (aligned with the input image of the current state), where each pixel represents a local navigational endpoint at the corresponding scene location. Using ConvNets to infer spatial action maps from state images, action predictions are thereby spatially anchored on local visual features in the scene, enabling significantly faster learning of complex behaviors for mobile manipulation tasks with reinforcement learning. In our experiments, we task a robot with pushing objects to a goal location, and find that policies learned with spatial action maps achieve much better performance than traditional alternatives.
View details
Form2Fit: Learning Shape Priors for Generalizable Assembly from Disassembly
Kevin Zakka
Andy Zeng
Shuran Song
IEEE International Conference on Robotics and Automation (ICRA) (2020)
Preview abstract
Is it possible to learn policies for robotic assembly that can generalize to new objects? We explore this idea in the context of the kit assembly task. Since classic methods rely heavily on object pose estimation, they often struggle to generalize to new objects without 3D CAD models or task-specific training data. In this work, we propose to formulate the kit assembly task as a shape matching problem, where the goal is to learn a shape descriptor that establishes geometric correspondences between object surfaces and their target placement locations from visual input. This formulation enables the model to acquire a broader understanding of how shapes and surfaces fit together for assembly – allowing it to generalize to new objects and kits. To obtain training data for our model, we present a self-supervised data-collection pipeline that obtains ground truth object-to-placement correspondences by disassembling complete kits. Our resulting real-world system, Form2Fit, learns effective pick and place strategies for assembling objects into a variety of kits – achieving 90% average success rates under different initial conditions (e.g. varying object and kit poses), 94% success under new configurations of multiple kits, and over 86% success with completely new objects and kits.
View details
Grasping in the Wild: Learning 6DoF Closed-Loop Grasping from Low-Cost Demonstrations
Shuran Song
Andy Zeng
IEEE Robotics and Automation Letters (RA-L) (2020)
Preview abstract
Intelligent manipulation benefits from the capacity to flexibly control an end-effector with high degrees of freedom (DoF) and dynamically react to the environment. However, due to the challenges of collecting effective training data and learning efficiently, most grasping algorithms today are limited to top-down movements and open-loop execution. In this work, we propose a new low-cost hardware interface for collecting grasping demonstrations by people in diverse environments. Leveraging this data, we show that it is possible to train a robust end-to-end 6DoF closed-loop grasping model with reinforcement learning that transfers to real robots. A key aspect of our grasping model is that it uses “action-view” based rendering to simulate future states with respect to different possible actions. By evaluating these states using a learned value function (Q-function), our method is able to better select corresponding actions that maximize total rewards (i.e., grasping success). Our final grasping system is able to achieve reliable 6DoF closed-loop grasping of novel objects across various scene configurations, as well as dynamic scenes with moving objects.
View details
