Visual programming has the potential of providing novice programmers with a low-code experience to build customized processing pipelines.Existing systems typically require users to build pipelines from scratch, implying that novice users are expected to set up and link appropriate nodes from a blank workspace.In this paper, we introduce InstructPipe, an AI assistant for prototyping machine learning (ML) pipelines with text instructions.We contribute two large language model (LLM) modules and a code interpreter as part of our framework.The LLM modules generate pseudocode for a target pipeline, and the interpreter renders the pipeline in the node-graph editor for further human-AI collaboration.Both technical and user evaluation (N=16) shows that InstructPipe empowers users to streamline their ML pipeline workfow, reduce their learning curve, and leverage open-ended commands to spark innovative ideas.

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.

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 cloud robotics platform that enables low-latency remote execution of control policies on physical robots, we present the first systematic benchmarking of fabric manipulation al-gorithms 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 was performed remotely without physical access to the robot workcell. Results suggest a new algorithm combining imitation learning with analytic methods achieves human-level performance on the flattening task and 93% of human-level performance on the folding task. See https://sites.google.com/berkeley.edu/ cloudfolding for all data, code, models, and supplemental material.

Transparent objects are a common part of everyday life, yet they possess unique visual properties that make them incredibly difficult for standard 3D sensors to produce accurate depth estimates for. In many cases, they often appear as noisy or distorted approximations of the surfaces that lie behind them. To address these challenges, we present ClearGrasp - a deep learning approach for estimating accurate 3D geometry of transparent objects from a single RGB-D image for robotic manipulation. Given a single RGB-D image of transparent objects, ClearGrasp uses deep convolutional networks to infer surface normals, masks of transparent surfaces, and occlusion boundaries. It then uses these outputs to refine the initial depth estimates for all transparent surfaces in the scene. To train and test ClearGrasp, we construct a large-scale synthetic dataset of over 50,000 RGB-D images, as well as a real-world test benchmark with 286 RGB-D images of transparent objects and their ground truth geometries. The experiments demonstrate that ClearGrasp is substantially better than monocular depth estimation baselines and is capable of generalizing to real-world images and novel objects. We also demonstrate that ClearGrasp can be applied out-of-the-box to improve grasping algorithms' performance on transparent objects. Code, data, and benchmarks will be released. Supplementary materials: https://sites.google.com/view/cleargrasp.

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. Code, videos, and supplemental material are available at https://form2fit.github.io.

We investigate whether a robot arm can learn to pick and throw arbitrary rigid objects into selected boxes quickly and accurately. Throwing has the potential to increase the physical reachability and picking speed of a robot arm. However, precisely throwing arbitrary objects in unstructured settings presents many challenges: from acquiring objects in grasps suitable for reliable throwing, to handling varying object-centric properties (e.g., mass distribution, friction, shape) and complex aerodynamics. In this work, we propose an end-to-end formulation that jointly learns to infer control parameters for grasping and throwing motion primitives from visual observations (RGB-D images of arbitrary objects in a bin) through trial and error. Within this formulation, we investigate the synergies between grasping and throwing (i.e., learning grasps that enable more accurate throws) and between simulation and deep learning (i.e., using deep networks to predict residuals on top of control parameters predicted by a physics simulator). The resulting system, TossingBot, is able to grasp and successfully throw arbitrary objects into boxes located outside its maximum reach range at 500+ mean picks per hour (600+ grasps per hour with 85% throwing accuracy); and generalizes to new objects and target locations.

Skilled robotic manipulation benefits from complex synergies between non-prehensile (e.g. pushing) and prehensile (e.g. grasping) actions: pushing can help rearrange cluttered objects to make space for arms and fingers; likewise, grasping can help displace objects to make pushing movements more precise and collision-free. In this work, we demonstrate that it is possible to discover and learn these synergies from scratch through model-free deep reinforcement learning. Our method involves training two fully convolutional networks that map from visual observations to actions: one infers the utility of pushes for a dense pixel-wise sampling of end-effector orientations and locations, while the other does the same for grasping. Both networks are trained jointly in a Q-learning framework and are entirely self-supervised by trial and error, where rewards are provided from successful grasps. In this way, our policy learns pushing motions that enable future grasps, while learning grasps that can leverage past pushes. During picking experiments in both simulation and real-world scenarios, we find that our system quickly learns complex behaviors even amid challenging cases of tightly packed clutter, and achieves better grasping success rates and picking efficiencies than baseline alternatives after a few hours of training. We further demonstrate that our method is capable of generalizing to novel objects. Qualitative results (videos), code, pre-trained models, and simulation environments are available at http://vpg.cs.princeton.edu/

Facebook's purchase of Oculus VR in 2014 ushered in a new era of consumer virtual reality head-mounted displays (HMDs). Converging technological advancements in small, high-resolution displays and motion-detection devices propelled VR beyond the purview of high-tech research laboratories and into the mainstream. However, technological hurdles still remain. As more consumer grade products develop, user comfort and experience will be of the utmost importance. One of the biggest issues for HMDs that lack external tracking is drift in the user position and rotation sensors. Drift can cause motion sickness and make stationary items in the virtual environment to appear to shift in position. For developers who seek to design VR experiences that are rooted in real environments, drift can create large errors in positional tracking if left uncorrected over time. Although much of the current VR hardware makes use of external tracking devices to mitigate positional and rotational drift, the creation of head-mounted displays that can operate without the use of extremal tracking devices would make VR hardware more portable and flexible, and may therefore be a goal for future development.

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 a robotic platform for the purpose of studying cognition. We suggest that the central component of cognition is a memory which is primarily associative, one where learning occurs as the correlation of events from diverse inputs. We also posit that human-like cognition requires a well-integrated sensory-motor system, to provide these diverse inputs. As implemented in our robot, this system includes binaural hearing, stereo vision, tactile sense, and basic proprioceptive control. On top of these abilities, we are implementing and studying various models of processing, learning and decision making. Our goal is to produce a robot that will learn to carry out simple tasks in response to natural language requests. The robot's understanding of language will be learned concurrently with its other cognitive abilities. We have already developed a robust system and conducted a number or experiments on the way to this goal, some details of which appear in this paper. This is a first progress report of what we believe will be a long term project with significant implications.