We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of daily-life activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception.

We investigate the problem of transferring an expert policy from a source robot to multiple different robots. To solve this problem, we propose a method named *Meta-Evolve* that uses continuous robot evolution to efficiently transfer the policy to each target robot through a set of tree-structured evolutionary robot sequences. The robot evolution tree allows the robot evolution paths to be shared, so our approach can significantly outperform naive one-to-one policy transfer. We present a heuristic approach to determine an optimized robot evolution tree. Experiments have shown that our method is able to improve the efficiency of one-to-three transfer of manipulation policy by up to 3.2$\times$ and one-to-six transfer of agile locomotion policy by 2.4$\times$ in terms of simulation cost over the baseline of launching multiple independent one-to-one policy transfers. Supplementary videos available at the project website: https://sites.google.com/view/meta-evolve.

Snake robots have showcased remarkable compliance and adaptability in their interaction with environments, mirroring the traits of their natural counterparts. While their hyper-redundant and high-dimensional characteristics add to this adaptability, they also pose great challenges to robot control. Instead of perceiving the hyper-redundancy and flexibility of snake robots as mere challenges, there lies an unexplored potential in leveraging these traits to enhance robustness and generalizability at the control policy level. We seek to develop a control policy that effectively breaks down the high dimensionality of snake robots while harnessing their redundancy. In this work, we consider the snake robot as a modular robot and formulate the control of the snake robot as a cooperative Multi-Agent Reinforcement Learning (MARL) problem. Each segment of the snake robot functions as an individual agent. Specifically, we incorporate a self-attention mechanism to enhance the cooperative behavior between agents. A high-level imagination policy is proposed to provide additional rewards to guide the low-level control policy. We validate the proposed method COMPOSER with five snake robot tasks, including goal reaching, wall climbing, shape formation, tube crossing, and block pushing. COMPOSER achieves the highest success rate across all tasks when compared to a centralized baseline and four modular policy baselines. Additionally, we show enhanced robustness against module corruption and significantly superior zero-shot generalizability in our proposed method. The videos of this work are available on our project page: https://sites.google.com/view/composer-snake/.

Quadrupedal robots have emerged as versatile agents capable of locomoting and manipulating in complex environments. Traditional designs typically rely on the robot’s inherent body parts or incorporate top-mounted arms for manipulation tasks. However, these configurations may limit the robot’s operational dexterity, efficiency, and adaptability, particularly in cluttered or constrained spaces. In this work, we present LocoMan, a dexterous quadrupedal robot with a novel morphology to perform versatile manipulation in diverse constrained environments. By equipping a Unitree Go1 robot with two low-cost and lightweight modular 3-DoF loco-manipulators on its front calves, LocoMan leverages the combined mobility and functionality of the legs and grippers for complex manipulation tasks that require precise 6D positioning of the end effector in a wide workspace. To harness the loco-manipulation capabilities of LocoMan, we introduce a unified control framework that extends the whole-body controller (WBC) to integrate the dynamics of loco-manipulators. Through experiments, we validate that the proposed whole-body controller can accurately and stably follow desired 6D trajectories of the end effector and torso, which, when combined with the large workspace from our design, facilitates a diverse set of challenging dexterous loco-manipulation tasks in confined spaces, such as opening doors, plugging into sockets, picking objects in narrow and low-lying spaces, and bimanual manipulation.

Accurately estimating 3D hand pose is crucial for understanding how humans interact with the world. Despite remarkable progress, existing methods often struggle to generate plausible hand poses when the hand is heavily occluded or blurred. In videos, the movements of the hand allow us to observe various parts of the hand that may be occluded or blurred in a single frame. To adaptively leverage the visual clue before and after the occlusion or blurring for robust hand pose estimation, we propose the Deformer: a framework that implicitly reasons about the relationship between hand parts within the same image (spatial dimension) and different timesteps (temporal dimension). We show that a naive application of the transformer self-attention mechanism is not sufficient because motion blur or occlusions in certain frames can lead to heavily distorted hand features and generate imprecise keys and queries. To address this challenge, we incorporate a Dynamic Fusion Module into Deformer, which predicts the deformation of the hand and warps the hand mesh predictions from nearby frames to explicitly support the current frame estimation. Furthermore, we have observed that errors are unevenly distributed across different hand parts, with vertices around fingertips having disproportionately higher errors than those around the palm. We mitigate this issue by introducing a new loss function called maxMSE that automatically adjusts the weight of every vertex to focus the model on critical hand parts. Extensive experiments show that our method significantly outperforms state-of-the-art methods by 10%, and is more robust to occlusions (over 14%).

A key component of understanding hand-object interactions is the ability to identify the active object-the object that is being manipulated by the human hand. In order to accurately localize the active object, any method must reason using information encoded by each image pixel, such as whether it belongs to the hand, the object, or the background. To leverage each pixel as evidence to determine the bounding box of the active object, we propose a pixel-wise voting function. Our pixel-wise voting function takes an initial bounding box as input and produces an improved bounding box of the active object as output. The voting function is designed so that each pixel inside of the input bounding box votes for an improved bounding box, and the box with the majority vote is selected as the output. We call the collection of bounding boxes generated inside of the voting function, the Relational Box Field, as it characterizes a field of bounding boxes defined in relationship to the current bounding box. While our voting function is able to improve the bounding box of the active object, one round of voting is typically not enough to accurately localize the active object. Therefore, we repeatedly apply the voting function to sequentially improve the location of the bounding box. However, since it is known that repeatedly applying a one-step predictor (i.e., auto-regressive processing with our voting function) can cause a data distribution shift, we mitigate this issue using reinforcement learning (RL). We adopt standard RL to learn the voting function parameters and show that it provides a meaningful improvement over a standard supervised learning approach. We perform experiments on two large-scale datasets: 100DOH and MECCANO, improving AP50 performance by 8% and 30%, respectively, over the state of the art. The project page with code and visualizations can be found at https://fuqichen1998.github.io/SequentialVotingDet/.

We introduce Ego4D, a massive-scale egocentric video dataset and benchmark suite. It offers 3,670 hours of dailylife activity video spanning hundreds of scenarios (household, outdoor, workplace, leisure, etc.) captured by 931 unique camera wearers from 74 worldwide locations and 9 different countries. The approach to collection is designed to uphold rigorous privacy and ethics standards, with consenting participants and robust de-identification procedures where relevant. Ego4D dramatically expands the volume of diverse egocentric video footage publicly available to the research community. Portions of the video are accompanied by audio, 3D meshes of the environment, eye gaze, stereo, and/or synchronized videos from multiple egocentric cameras at the same event. Furthermore, we present a host of new benchmark challenges centered around understanding the first-person visual experience in the past (querying an episodic memory), present (analyzing hand-object manipulation, audio-visual conversation, and social interactions), and future (forecasting activities). By publicly sharing this massive annotated dataset and benchmark suite, we aim to push the frontier of first-person perception. Project page: https://ego4d-data.org/

A popular paradigm in robotic learning is to train a policy from scratch for every new robot. This is not only inefficient but also often impractical for complex robots. In this work, we consider the problem of transferring a policy across two different robots with significantly different parameters such as kinematics and morphology. Existing approaches that train a new policy by matching the action or state transition distribution, including imitation learning methods, fail due to optimal action and/or state distribution being mismatched in different robots. In this paper, we propose a novel method named REvolveR of using continuous evolutionary models for robotic policy transfer implemented in a physics simulator. We interpolate between the source robot and the target robot by finding a continuous evolutionary change of robot parameters. An expert policy on the source robot is transferred through training on a sequence of intermediate robots that gradually evolve into the target robot. Experiments on a physics simulator show that the proposed continuous evolutionary model can effectively transfer the policy across robots and achieve superior sample efficiency on new robots. The proposed method is especially advantageous in sparse reward settings where exploration can be significantly reduced.

We present RePOSE, a fast iterative refinement method for 6D object pose estimation. Prior methods perform refinement by feeding zoomed-in input and rendered RGB images into a CNN and directly regressing an update of a refined pose. Their runtime is slow due to the computational cost of CNN, which is especially prominent in multiple-object pose refinement. To overcome this problem, RePOSE leverages image rendering for fast feature extraction using a 3D model with a learnable texture. We call this deep texture rendering, which uses a shallow multilayer perceptron to directly regress a view-invariant image representation of an object. Furthermore, we utilize differentiable Levenberg-Marquardt (LM) optimization to refine a pose fast and accurately by minimizing the distance between the input and rendered image representations without the need of zooming in. These image representations are trained such that differentiable LM optimization converges within few iterations. Consequently, RePOSE runs at 92 FPS and achieves state-of-the-art accuracy of 51.6% on the Occlusion LineMOD dataset - a 4.1% absolute improvement over the prior art, and comparable result on the YCB-Video dataset with a much faster runtime. The code is available at https://github.com/sh8/repose.

We present a large-scale stereo RGB image object pose estimation dataset named the StereOBJ-1M dataset. The dataset is designed to address challenging cases such as object transparency, translucency, and specular reflection, in addition to the common challenges of occlusion, symmetry, and variations in illumination and environments. In order to collect data of sufficient scale for modern deep learning models, we propose a novel method for efficiently annotating pose data in a multi-view fashion that allows data capturing in complex and flexible environments. Fully annotated with 6D object poses, our dataset contains over 396K frames and over 1.5M annotations of 18 objects recorded in 183 scenes constructed in 11 different environments. The 18 objects include 8 symmetric objects, 7 transparent objects, and 8 reflective objects. We benchmark two state-of-the-art pose estimation frameworks on StereOBJ-1M as baselines for future work. We also propose a novel object-level pose optimization method for computing 6D pose from keypoint predictions in multiple images.

We present KDFNet, a novel method for 6D object pose estimation from RGB images. To handle occlusion, many recent works have proposed to localize 2D keypoints through pixel-wise voting and solve a Perspective-n-Point (PnP) problem for pose estimation, which achieves leading performance. However, such voting process is direction-based and cannot handle long and thin objects where the direction intersections cannot be robustly found. To address this problem, we propose a novel continuous representation called Keypoint Distance Field (KDF) for projected 2D keypoint locations. Formulated as a 2D array, each element of the KDF stores the 2D Euclidean distance between the corresponding image pixel and a specified projected 2D keypoint. We use a fully convolutional neural network to regress the KDF for each keypoint. Using this KDF encoding of projected object keypoint locations, we propose to use a distance-based voting scheme to localize the keypoints by calculating circle intersections in a RANSAC fashion. We validate the design choices of our framework by extensive ablation experiments. Our proposed method achieves state-of-the-art performance on Occlusion LINEMOD dataset with an average ADD(-S) accuracy of 50.3% and TOD dataset mug subset with an average ADD accuracy of 75.72%. Extensive experiments and visualizations demonstrate that the proposed method is able to robustly estimate the 6D pose in challenging scenarios including occlusion.

Estimating the 3D pose of desktop objects is crucial for applications such as robotic manipulation. Many existing approaches to this problem require a depth map of the object for both training and prediction, which restricts them to opaque, lambertian objects that produce good returns in an RGBD sensor. In this paper we forgo using a depth sensor in favor of raw stereo input. We address two problems: first, we establish an easy method for capturing and labeling 3D keypoints on desktop objects with an RGB camera; and second, we develop a deep neural network, called KeyPose, that learns to accurately predict object poses using 3D keypoints, from stereo input, and works even for transparent objects. To evaluate the performance of our method, we create a dataset of 15 clear objects in five classes, with 48K 3D-keypoint labeled images. We train both instance and category models, and show generalization to new textures, poses, and objects. KeyPose surpasses state-of-the-art performance in 3D pose estimation on this dataset by factors of 1.5 to 3.5, even in cases where the competing method is provided with ground-truth depth. Stereo input is essential for this performance as it improves results compared to using monocular input by a factor of 2. We will release a public version of the data capture and labeling pipeline, the transparent object database, and the KeyPose models and evaluation code. Project website: https://sites.google.com/corp/view/keypose.

Correspondences between frames encode rich information about dynamic content in videos. However, it is challenging to effectively capture and learn those due to their irregular structure and complex dynamics. In this paper, we propose a novel neural network that learns video representations by aggregating information from potential correspondences. This network, named CPNet, can learn evolving 2D fields with temporal consistency. In particular, it can effectively learn representations for videos by mixing appearance and long-range motion with an RGB-only input. We provide extensive ablation experiments to validate our model. CPNet shows stronger performance than existing methods on Kinetics and achieves the state-of-the-art performance on Something-Something and Jester. We provide analysis towards the behavior of our model and show its robustness to errors in proposals.

Many applications in robotics and human-computer interaction can benefit from understanding 3D motion of points in a dynamic environment, widely noted as scene flow. While most previous methods focus on stereo and RGB-D images as input, few try to estimate scene flow directly from point clouds. In this work, we propose a novel deep neural network named FlowNet3D that learns scene flow from point clouds in an end-to-end fashion. Our network simultaneously learns deep hierarchical features of point clouds and flow embeddings that represent point motions, supported by two newly proposed learning layers for point sets. We evaluate the network on both challenging synthetic data from FlyingThings3D and real Lidar scans from KITTI. Trained on synthetic data only, our network successfully generalizes to real scans, outperforming various baselines and showing competitive results to the prior art. We also demonstrate two applications of our scene flow output (scan registration and motion segmentation) to show its potential wide use cases.

Understanding dynamic 3D environment is crucial for robotic agents and many other applications. We propose a novel neural network architecture called MeteorNet for learning representations for dynamic 3D point cloud sequences. Different from previous work that adopts a grid-based representation and applies 3D or 4D convolutions, our network directly processes point clouds. We propose two ways to construct spatiotemporal neighborhoods for each point in the point cloud sequence. Information from these neighborhoods is aggregated to learn features per point. We benchmark our network on a variety of 3D recognition tasks including action recognition, semantic segmentation and scene flow estimation. MeteorNet shows stronger performance than previous grid-based methods while achieving state-of-the-art performance on Synthia. MeteorNet also outperforms previous baseline methods that are able to process at most two consecutive point clouds. To the best of our knowledge, this is the first work on deep learning for dynamic raw point cloud sequences.

State-of-the-art deep neural networks (DNNs) have hundreds of millions of connections and are both computationally and memory intensive, making them difficult to deploy on embedded systems with limited hardware resources and power budgets. While custom hardware helps the computation, fetching weights from DRAM is two orders of magnitude more expensive than ALU operations, and dominates the required power. Previously proposed 'Deep Compression' makes it possible to fit large DNNs (AlexNet and VGGNet) fully in on-chip SRAM. This compression is achieved by pruning the redundant connections and having multiple connections share the same weight. We propose an energy efficient inference engine (EIE) that performs inference on this compressed network model and accelerates the resulting sparse matrix-vector multiplication with weight sharing. Going from DRAM to SRAM gives EIE 120x energy saving, Exploiting sparsity saves 10x, Weight sharing gives 8x, Skipping zero activations from ReLU saves another 3x. Evaluated on nine DNN benchmarks, EIE is 189x and 13x faster when compared to CPU and GPU implementations of the same DNN without compression. EIE has a processing power of 102 GOPS working directly on a compressed network, corresponding to 3 TOPS on an uncompressed network, and processes FC layers of AlexNet at 1.88x104 frames/sec with a power dissipation of only 600mW. It is 24,000x and 3,400x more energy efficient than a CPU and GPU respectively. Compared with DaDianNao, EIE has 2.9x, 19x and 3x better throughput, energy efficiency and area efficiency.