Search

Legged locomotion over various terrains is challenging and requires precise perception of the robot and its surroundings from both proprioception and vision. However, learning directly from high-dimensional visual input is often data-inefficient and intricate. To address this issue, traditional methods attempt to learn a teacher policy with access to privileged information first and then learn a student policy to imitate the teacher's behavior with visual input. Despite some progress, this imitation framework prevents the student policy from achieving optimal performance due to the information gap between inputs. Furthermore, the learning process is unnatural since animals intuitively learn to traverse different terrains based on their understanding of the world without privileged knowledge. Inspired by this natural ability, we propose a simple yet effective method, World Model-based Perception (WMP), which builds a world model of the environment and learns a policy based on the world model. We illustrate that though completely trained in simulation, the world model can make accurate predictions of real-world trajectories, thus providing informative signals for the policy controller. Extensive simulated and real-world experiments demonstrate that WMP outperforms state-of-the-art baselines in traversability and robustness. Videos and Code are available at: https://wmp-loco.github.io/., Comment: under review

The robotics community has consistently aimed to achieve generalizable robot manipulation with flexible natural language instructions. One of the primary challenges is that obtaining robot data fully annotated with both actions and texts is time-consuming and labor-intensive. However, partially annotated data, such as human activity videos without action labels and robot play data without language labels, is much easier to collect. Can we leverage these data to enhance the generalization capability of robots? In this paper, we propose GR-MG, a novel method which supports conditioning on both a language instruction and a goal image. During training, GR-MG samples goal images from trajectories and conditions on both the text and the goal image or solely on the image when text is unavailable. During inference, where only the text is provided, GR-MG generates the goal image via a diffusion-based image-editing model and condition on both the text and the generated image. This approach enables GR-MG to leverage large amounts of partially annotated data while still using language to flexibly specify tasks. To generate accurate goal images, we propose a novel progress-guided goal image generation model which injects task progress information into the generation process, significantly improving the fidelity and the performance. In simulation experiments, GR-MG improves the average number of tasks completed in a row of 5 from 3.35 to 4.04. In real-robot experiments, GR-MG is able to perform 47 different tasks and improves the success rate from 62.5% to 75.0% and 42.4% to 57.6% in simple and generalization settings, respectively. Code and checkpoints will be available at the project page: https://gr-mg.github.io/., Comment: 9 pages, 7 figures, letter

The outdoor vision systems are frequently contaminated by rain streaks and raindrops, which significantly degenerate the performance of visual tasks and multimedia applications. The nature of videos exhibits redundant temporal cues for rain removal with higher stability. Traditional video deraining methods heavily rely on optical flow estimation and kernel-based manners, which have a limited receptive field. Yet, transformer architectures, while enabling long-term dependencies, bring about a significant increase in computational complexity. Recently, the linear-complexity operator of the state space models (SSMs) has contrarily facilitated efficient long-term temporal modeling, which is crucial for rain streaks and raindrops removal in videos. Unexpectedly, its uni-dimensional sequential process on videos destroys the local correlations across the spatio-temporal dimension by distancing adjacent pixels. To address this, we present an improved SSMs-based video deraining network (RainMamba) with a novel Hilbert scanning mechanism to better capture sequence-level local information. We also introduce a difference-guided dynamic contrastive locality learning strategy to enhance the patch-level self-similarity learning ability of the proposed network. Extensive experiments on four synthesized video deraining datasets and real-world rainy videos demonstrate the effectiveness and efficiency of our network in the removal of rain streaks and raindrops. Our code and results are available at https://github.com/TonyHongtaoWu/RainMamba., Comment: ACM Multimedia 2024 Oral

Scalable robot learning in the real world is limited by the cost and safety issues of real robots. In addition, rolling out robot trajectories in the real world can be time-consuming and labor-intensive. In this paper, we propose to learn an interactive real-robot action simulator as an alternative. We introduce a novel method, IRASim, which leverages the power of generative models to generate extremely realistic videos of a robot arm that executes a given action trajectory, starting from an initial given frame. To validate the effectiveness of our method, we create a new benchmark, IRASim Benchmark, based on three real-robot datasets and perform extensive experiments on the benchmark. Results show that IRASim outperforms all the baseline methods and is more preferable in human evaluations. We hope that IRASim can serve as an effective and scalable approach to enhance robot learning in the real world. To promote research for generative real-robot action simulators, we open-source code, benchmark, and checkpoints at https: //gen-irasim.github.io., Comment: Opensource, project website: https://gen-irasim.github.io

Real-world vision tasks frequently suffer from the appearance of unexpected adverse weather conditions, including rain, haze, snow, and raindrops. In the last decade, convolutional neural networks and vision transformers have yielded outstanding results in single-weather video removal. However, due to the absence of appropriate adaptation, most of them fail to generalize to other weather conditions. Although ViWS-Net is proposed to remove adverse weather conditions in videos with a single set of pre-trained weights, it is seriously blinded by seen weather at train-time and degenerates when coming to unseen weather during test-time. In this work, we introduce test-time adaptation into adverse weather removal in videos, and propose the first framework that integrates test-time adaptation into the iterative diffusion reverse process. Specifically, we devise a diffusion-based network with a novel temporal noise model to efficiently explore frame-correlated information in degraded video clips at training stage. During inference stage, we introduce a proxy task named Diffusion Tubelet Self-Calibration to learn the primer distribution of test video stream and optimize the model by approximating the temporal noise model for online adaptation. Experimental results, on benchmark datasets, demonstrate that our Test-Time Adaptation method with Diffusion-based network(Diff-TTA) outperforms state-of-the-art methods in terms of restoring videos degraded by seen weather conditions. Its generalizable capability is also validated with unseen weather conditions in both synthesized and real-world videos.

Generative pre-trained models have demonstrated remarkable effectiveness in language and vision domains by learning useful representations. In this paper, we extend the scope of this effectiveness by showing that visual robot manipulation can significantly benefit from large-scale video generative pre-training. We introduce GR-1, a straightforward GPT-style model designed for multi-task language-conditioned visual robot manipulation. GR-1 takes as inputs a language instruction, a sequence of observation images, and a sequence of robot states. It predicts robot actions as well as future images in an end-to-end manner. Thanks to a flexible design, GR-1 can be seamlessly finetuned on robot data after pre-trained on a large-scale video dataset. We perform extensive experiments on the challenging CALVIN benchmark and a real robot. On CALVIN benchmark, our method outperforms state-of-the-art baseline methods and improves the success rate from 88.9% to 94.9%. In the setting of zero-shot unseen scene generalization, GR-1 improves the success rate from 53.3% to 85.4%. In real robot experiments, GR-1 also outperforms baseline methods and shows strong potentials in generalization to unseen scenes and objects. We provide inaugural evidence that a unified GPT-style transformer, augmented with large-scale video generative pre-training, exhibits remarkable generalization to multi-task visual robot manipulation. Project page: https://GR1-Manipulation.github.io, Comment: Project page: https://GR1-Manipulation.github.io

Recent progress in vision language foundation models has shown their ability to understand multimodal data and resolve complicated vision language tasks, including robotics manipulation. We seek a straightforward way of making use of existing vision-language models (VLMs) with simple fine-tuning on robotics data. To this end, we derive a simple and novel vision-language manipulation framework, dubbed RoboFlamingo, built upon the open-source VLMs, OpenFlamingo. Unlike prior works, RoboFlamingo utilizes pre-trained VLMs for single-step vision-language comprehension, models sequential history information with an explicit policy head, and is slightly fine-tuned by imitation learning only on language-conditioned manipulation datasets. Such a decomposition provides RoboFlamingo the flexibility for open-loop control and deployment on low-performance platforms. By exceeding the state-of-the-art performance with a large margin on the tested benchmark, we show RoboFlamingo can be an effective and competitive alternative to adapt VLMs to robot control. Our extensive experimental results also reveal several interesting conclusions regarding the behavior of different pre-trained VLMs on manipulation tasks. We believe RoboFlamingo has the potential to be a cost-effective and easy-to-use solution for robotics manipulation, empowering everyone with the ability to fine-tune their own robotics policy., Comment: Fix typos. Project page: https://roboflamingo.github.io

In this paper, we present a novel method for mobile manipulators to perform multiple contact-rich manipulation tasks. While learning-based methods have the potential to generate actions in an end-to-end manner, they often suffer from insufficient action accuracy and robustness against noise. On the other hand, classical control-based methods can enhance system robustness, but at the cost of extensive parameter tuning. To address these challenges, we present MOMA-Force, a visual-force imitation method that seamlessly combines representation learning for perception, imitation learning for complex motion generation, and admittance whole-body control for system robustness and controllability. MOMA-Force enables a mobile manipulator to learn multiple complex contact-rich tasks with high success rates and small contact forces. In a real household setting, our method outperforms baseline methods in terms of task success rates. Moreover, our method achieves smaller contact forces and smaller force variances compared to baseline methods without force imitation. Overall, we offer a promising approach for efficient and robust mobile manipulation in the real world. Videos and more details can be found on \url{https://visual-force-imitation.github.io}, Comment: IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2023

In this letter, a paradigm for the classification and manipulation of previously unseen objects is established and demonstrated through a real example of chairs. We present a novel robot manipulation method, guided by the understanding of object stability, perceptibility, and affordance, which allows the robot to prepare previously unseen and randomly oriented chairs for a teddy bear to sit on. Specifically, the robot encounters an unknown object and first reconstructs a complete 3D model from perceptual data via active and autonomous manipulation. By inserting this model into a physical simulator (i.e., the robot's "imagination"), the robot assesses whether the object is a chair and determines how to reorient it properly to be used, i.e., how to reorient it to an upright and accessible pose. If the object is classified as a chair, the robot reorients the object to this pose and seats the teddy bear onto the chair. The teddy bear is a proxy for an elderly person, hospital patient, or child. Experiment results show that our method achieves a high success rate on the real robot task of chair preparation. Also, it outperforms several baseline methods on the task of upright pose prediction for chairs.

As an effective method to deliver external materials into biological cells, microinjection has been widely applied in the biomedical field. However, the cognition of cell mechanical property is still inadequate, which greatly limits the efficiency and success rate of injection. Thus, a new rate-dependent mechanical model based on membrane theory is proposed for the first time. In this model, an analytical equilibrium equation between the injection force and cell deformation is established by considering the speed effect of microinjection. Different from the traditional membrane-theory-based model, the elastic coefficient of the constitutive material in the proposed model is modified as a function of the injection velocity and acceleration, effectively simulating the influence of speeds on the mechanical responses and providing a more generalized and practical model. Using this model, other mechanical responses at different speeds can be also accurately predicted, including the distribution of membrane tension and stress and the deformed shape. To verify the validity of the model, numerical simulations and experiments are carried out. The results show that the proposed model can match the real mechanical responses well at different injection speeds., Comment: 10 pages, 12 figures, submitted to IEEE TMech

Rearrangement tasks have been identified as a crucial challenge for intelligent robotic manipulation, but few methods allow for precise construction of unseen structures. We propose a visual foresight model for pick-and-place rearrangement manipulation which is able to learn efficiently. In addition, we develop a multi-modal action proposal module which builds on the Goal-Conditioned Transporter Network, a state-of-the-art imitation learning method. Our image-based task planning method, Transporters with Visual Foresight, is able to learn from only a handful of data and generalize to multiple unseen tasks in a zero-shot manner. TVF is able to improve the performance of a state-of-the-art imitation learning method on unseen tasks in simulation and real robot experiments. In particular, the average success rate on unseen tasks improves from 55.4% to 78.5% in simulation experiments and from 30% to 63.3% in real robot experiments when given only tens of expert demonstrations. Video and code are available on our project website: https://chirikjianlab.github.io/tvf/, Comment: IEEE IROS 2022

In this paper, we study the problem of autonomously seating a teddy bear on a previously unseen chair. To achieve this goal, we present a novel method for robots to imagine the sitting pose of the bear by physically simulating a virtual humanoid agent sitting on the chair. We also develop a robotic system which leverages motion planning to plan SE(2) motions for a humanoid robot to walk to the chair and whole-body motions to put the bear on it. Furthermore, to cope with cases where the chair is not in an accessible pose for placing the bear, a human assistance module is introduced for a human to follow language instructions given by the robot to rotate the chair and help make the chair accessible. We implement our method with a robot arm and a humanoid robot. We calibrate the proposed system with 3 chairs and test on 12 previously unseen chairs in both accessible and inaccessible poses extensively. Results show that our method enables the robot to autonomously seat the teddy bear on the 12 previously unseen chairs with a very high success rate. The human assistance module is also shown to be very effective in changing the accessibility of the chair. Video demos and more details are available at https://chirikjianlab.github.io/putbearonchair/., Comment: IEEE ICRA 2022. Video demos are available at https://chirikjianlab.github.io/putbearonchair/

Path planning has long been one of the major research areas in robotics, with PRM and RRT being two of the most effective classes of planners. Though generally very efficient, these sampling-based planners can become computationally expensive in the important case of "narrow passages". This paper develops a path planning paradigm specifically formulated for narrow passage problems. The core is based on planning for rigid-body robots encapsulated by unions of ellipsoids. Each environmental feature is represented geometrically using a strictly convex body with a $\mathcal{C}^1$ boundary (e.g., superquadric). The main benefit of doing this is that configuration-space obstacles can be parameterized explicitly in closed form, thereby allowing prior knowledge to be used to avoid sampling infeasible configurations. Then, by characterizing a tight volume bound for multiple ellipsoids, robot transitions involving rotations are guaranteed to be collision-free without needing to perform traditional collision detection. Furthermore, by combining with a stochastic sampling strategy, the proposed planning framework can be extended to solving higher dimensional problems in which the robot has a moving base and articulated appendages. Benchmark results show that the proposed framework often outperforms the sampling-based planners in terms of computational time and success rate in finding a path through narrow corridors for both single-body robots and those with higher dimensional configuration spaces. Physical experiments using the proposed framework are further demonstrated on a humanoid robot that walks in several cluttered environments with narrow passages., Comment: 17 pages, 14 figures

Probabilistic point cloud registration methods are becoming more popular because of their robustness. However, unlike point-to-plane variants of iterative closest point (ICP) which incorporate local surface geometric information such as surface normals, most probabilistic methods (e.g., coherent point drift (CPD)) ignore such information and build Gaussian mixture models (GMMs) with isotropic Gaussian covariances. This results in sphere-like GMM components which only penalize the point-to-point distance between the two point clouds. In this paper, we propose a novel method called CPD with Local Surface Geometry (LSG-CPD) for rigid point cloud registration. Our method adaptively adds different levels of point-to-plane penalization on top of the point-to-point penalization based on the flatness of the local surface. This results in GMM components with anisotropic covariances. We formulate point cloud registration as a maximum likelihood estimation (MLE) problem and solve it with the Expectation-Maximization (EM) algorithm. In the E step, we demonstrate that the computation can be recast into simple matrix manipulations and efficiently computed on a GPU. In the M step, we perform an unconstrained optimization on a matrix Lie group to efficiently update the rigid transformation of the registration. The proposed method outperforms state-of-the-art algorithms in terms of accuracy and robustness on various datasets captured with range scanners, RGBD cameras, and LiDARs. Also, it is significantly faster than modern implementations of CPD. The source code is available at https://github.com/ChirikjianLab/LSG-CPD.git., Comment: Accepted to ICCV 2021

Open containers, i.e., containers without covers, are an important and ubiquitous class of objects in human life. In this letter, we propose a novel method for robots to "imagine" the open containability affordance of a previously unseen object via physical simulations. We implement our imagination method on a UR5 manipulator. The robot autonomously scans the object with an RGB-D camera. The scanned 3D model is used for open containability imagination which quantifies the open containability affordance by physically simulating dropping particles onto the object and counting how many particles are retained in it. This quantification is used for open-container vs. non-open-container binary classification (hereafter referred to as open container classification). If the object is classified as an open container, the robot further imagines pouring into the object, again using physical simulations, to obtain the pouring position and orientation for real robot autonomous pouring. We evaluate our method on open container classification and autonomous pouring of granular material on a dataset containing 130 previously unseen objects with 57 object categories. Although our proposed method uses only 11 objects for simulation calibration (training), its open container classification aligns well with human judgements. In addition, our method endows the robot with the capability to autonomously pour into the 55 containers in the dataset with a very high success rate. We also compare to a deep learning method. Results show that our method achieves the same performance as the deep learning method on open container classification and outperforms it on autonomous pouring. Moreover, our method is fully explainable., Comment: IEEE Robotics and Automation Letters. Video demos are available on https://chirikjianlab.github.io/realcontainerimagination/

Recently, large-scale datasets have vastly facilitated the development in nearly all domains of Natural Language Processing. However, there is currently no cross-task dataset in NLP, which hinders the development of multi-task learning. We propose MATINF, the first jointly labeled large-scale dataset for classification, question answering and summarization. MATINF contains 1.07 million question-answer pairs with human-labeled categories and user-generated question descriptions. Based on such rich information, MATINF is applicable for three major NLP tasks, including classification, question answering, and summarization. We benchmark existing methods and a novel multi-task baseline over MATINF to inspire further research. Our comprehensive comparison and experiments over MATINF and other datasets demonstrate the merits held by MATINF., Comment: Accepted as a long paper at ACL 2020

This paper presents a new fractional-order normalized Bouc-Wen (BW) (FONBW) model to describe the asymmetric and rate-dependent hysteresis nonlinearity of piezoelectric actuators (PEAs). In view of the fact that the classical BW (CBW) model is only efficient for the symmetric and rate-independent hysteresis description, the FONBW model is devoted to characterizing the asymmetric and rate-dependent behaviors of the hysteresis in PEAs by adopting an Nth-order polynomial input function and two fractional operators, respectively. Different from the traditional modified BW models, the proposed FONBW model also eliminates the redundancy of parameters in the CBW model via the normalization processing. By this way, the developed FONBW model has a relatively simple mathematic expression with fewer parameters to simultaneously characterize the asymmetric and rate-dependent hysteresis behaviors of PEAs. Model parameters are identified by the self-adaptive differential evolution algorithm. To validate the effectiveness of the proposed model, a series of model verification and inverse-multiplicative-structure-based feedforward control experiments are carried out on a PEA system. Results show that the proposed model is superior to the CBW model and traditional modified BW model in modeling accuracy and hysteresis compensation., Comment: 9 pages, 10 figures, submitted to TMech; 10 pages, 11 figures, add two subsections in Section IV; modify Tables I and III, and Figures 9 and 10

Current Reinforcement Learning (RL) algorithms struggle with long-horizon tasks where time can be wasted exploring dead ends and task progress may be easily reversed. We develop the SPOT framework, which explores within action safety zones, learns about unsafe regions without exploring them, and prioritizes experiences that reverse earlier progress to learn with remarkable efficiency. The SPOT framework successfully completes simulated trials of a variety of tasks, improving a baseline trial success rate from 13% to 100% when stacking 4 cubes, from 13% to 99% when creating rows of 4 cubes, and from 84% to 95% when clearing toys arranged in adversarial patterns. Efficiency with respect to actions per trial typically improves by 30% or more, while training takes just 1-20k actions, depending on the task. Furthermore, we demonstrate direct sim to real transfer. We are able to create real stacks in 100% of trials with 61% efficiency and real rows in 100% of trials with 59% efficiency by directly loading the simulation-trained model on the real robot with no additional real-world fine-tuning. To our knowledge, this is the first instance of reinforcement learning with successful sim to real transfer applied to long term multi-step tasks such as block-stacking and row-making with consideration of progress reversal. Code is available at https://github.com/jhu-lcsr/good_robot ., Comment: Accepted to the journal IEEE Robotics and Automation Letters (RA-L) and to be presented at IROS 2020. This is a minor update to v3. 8 pages, 6 figures, 3 tables, 1 algorithm. Code is available at https://github.com/jhu-lcsr/good_robot and a video overview is at https://youtu.be/MbCuEZadkIw

For robots to exhibit a high level of intelligence in the real world, they must be able to assess objects for which they have no prior knowledge. Therefore, it is crucial for robots to perceive object affordances by reasoning about physical interactions with the object. In this paper, we propose a novel method to provide robots with an ability to imagine object affordances using physical simulations. The class of chair is chosen here as an initial category of objects to illustrate a more general paradigm. In our method, the robot "imagines" the affordance of an arbitrarily oriented object as a chair by simulating a physical sitting interaction between an articulated human body and the object. This object affordance reasoning is used as a cue for object classification (chair vs non-chair). Moreover, if an object is classified as a chair, the affordance reasoning can also predict the upright pose of the object which allows the sitting interaction to take place. We call this type of poses the functional pose. We demonstrate our method in chair classification on synthetic 3D CAD models. Although our method uses only 30 models for training, it outperforms appearance-based deep learning methods, which require a large amount of training data, when the upright orientation is not assumed to be known a priori. In addition, we showcase that the functional pose predictions of our method align well with human judgments on both synthetic models and real objects scanned by a depth camera., Comment: 7 pages, 6 figures. Accepted to ICRA2020