Jingxi Xu

Jingxi Xu, Shuran Song, Matei Ciocarlie

Inspired by the human ability to perform complex manipulation in the complete absence of vision (like retrieving an object from a pocket), the robotic manipulation field is motivated to develop new methods for tactile-based object interaction. However, tactile sensing presents the challenge of being an active sensing modality: a touch sensor provides sparse, local data, and must be used in conjunction with effective exploration strategies in order to collect information. In this work, we focus on the process of guiding tactile exploration, and its interplay with task-related decision making. We propose TANDEM (TActile exploration aNd DEcision Making), an architecture to learn efficient exploration strategies in conjunction with decision making. Our approach is based on separate but co-trained modules for exploration and discrimination. We demonstrate this method on a tactile object recognition task, where a robot equipped with a touch sensor must explore and identify an object from a known set based on binary contact signals alone. TANDEM achieves higher accuracy with fewer actions than alternative methods and is also shown to be more robust to sensor noise.

Jingxi Xu, Han Lin, Shuran Song et al.

Tactile recognition of 3D objects remains a challenging task. Compared to 2D shapes, the complex geometry of 3D surfaces requires richer tactile signals, more dexterous actions, and more advanced encoding techniques. In this work, we propose TANDEM3D, a method that applies a co-training framework for exploration and decision making to 3D object recognition with tactile signals. Starting with our previous work, which introduced a co-training paradigm for 2D recognition problems, we introduce a number of advances that enable us to scale up to 3D. TANDEM3D is based on a novel encoder that builds 3D object representation from contact positions and normals using PointNet++. Furthermore, by enabling 6DOF movement, TANDEM3D explores and collects discriminative touch information with high efficiency. Our method is trained entirely in simulation and validated with real-world experiments. Compared to state-of-the-art baselines, TANDEM3D achieves higher accuracy and a lower number of actions in recognizing 3D objects and is also shown to be more robust to different types and amounts of sensor noise. Video is available at https://jxu.ai/tandem3d.

Shuang Wu, Youtian Lin, Feihu Zhang et al.

Generating high-quality 3D assets from text and images has long been challenging, primarily due to the absence of scalable 3D representations capable of capturing intricate geometry distributions. In this work, we introduce Direct3D, a native 3D generative model scalable to in-the-wild input images, without requiring a multiview diffusion model or SDS optimization. Our approach comprises two primary components: a Direct 3D Variational Auto-Encoder (D3D-VAE) and a Direct 3D Diffusion Transformer (D3D-DiT). D3D-VAE efficiently encodes high-resolution 3D shapes into a compact and continuous latent triplane space. Notably, our method directly supervises the decoded geometry using a semi-continuous surface sampling strategy, diverging from previous methods relying on rendered images as supervision signals. D3D-DiT models the distribution of encoded 3D latents and is specifically designed to fuse positional information from the three feature maps of the triplane latent, enabling a native 3D generative model scalable to large-scale 3D datasets. Additionally, we introduce an innovative image-to-3D generation pipeline incorporating semantic and pixel-level image conditions, allowing the model to produce 3D shapes consistent with the provided conditional image input. Extensive experiments demonstrate the superiority of our large-scale pre-trained Direct3D over previous image-to-3D approaches, achieving significantly better generation quality and generalization ability, thus establishing a new state-of-the-art for 3D content creation. Project page: https://nju-3dv.github.io/projects/Direct3D/.

Jingxi Xu, Yinsen Jia, Dongxiao Yang et al.

We introduce GEOTACT, a robotic manipulation method capable of retrieving objects buried in granular media. This is a challenging task due to the need to interact with granular media, and doing so based exclusively on tactile feedback, since a buried object can be completely hidden from vision. Tactile feedback is in itself challenging in this context, due to ubiquitous contact with the surrounding media, and the inherent noise level induced by the tactile readings. To address these challenges, we use a learning method trained end-to-end with simulated sensor noise. We show that our problem formulation leads to the natural emergence of learned pushing behaviors that the manipulator uses to reduce uncertainty and funnel the object to a stable grasp despite spurious and noisy tactile readings. We also introduce a training curriculum that enables learning these behaviors in simulation, followed by zero-shot transfer to real hardware. To the best of our knowledge, GEOTACT is the first method to reliably retrieve a number of different objects from a granular environment, doing so on real hardware and with integrated tactile sensing. Videos and additional information can be found at https://jxu.ai/geotact.

Jingxi Xu, Ava Chen, Lauren Winterbottom et al.

Intent inferral, the process by which a robotic device predicts a user's intent from biosignals, offers an effective and intuitive way to control wearable robots. Classical intent inferral methods treat biosignal inputs as unidirectional ground truths for training machine learning models, where the internal state of the model is not directly observable by the user. In this work, we propose reciprocal learning, a bidirectional paradigm that facilitates human adaptation to an intent inferral classifier. Our paradigm consists of iterative, interwoven stages that alternate between updating machine learning models and guiding human adaptation with the use of augmented visual feedback. We demonstrate this paradigm in the context of controlling a robotic hand orthosis for stroke, where the device predicts open, close, and relax intents from electromyographic (EMG) signals and provides appropriate assistance. We use LED progress-bar displays to communicate to the user the predicted probabilities for open and close intents by the classifier. Our experiments with stroke subjects show reciprocal learning improving performance in a subset of subjects (two out of five) without negatively impacting performance on the others. We hypothesize that, during reciprocal learning, subjects can learn to reproduce more distinguishable muscle activation patterns and generate more separable biosignals.

Jingxi Xu

Unlike in language or vision, one of the fundamental challenges in robot learning is the lack of access to vast data resources. We can further break down the problem into (1) data sparsity from the angle of data representation and (2) data scarcity from the angle of data quantity. In this thesis, I will discuss selected works on two domains: (1) tactile sensing and (2) rehabilitation robots, which are exemplars of data sparsity and scarcity, respectively. Tactile sensing is an essential modality for robotics, but tactile data are often sparse, and for each interaction with the physical world, tactile sensors can only obtain information about the local area of contact. I will discuss my work on learning vision-free tactile-only exploration and manipulation policies through model-free reinforcement learning to make efficient use of sparse tactile information. On the other hand, rehabilitation robots are an example of data scarcity to the extreme due to the significant challenge of collecting biosignals from disabled-bodied subjects at scale for training. I will discuss my work in collaboration with the medical school and clinicians on intent inferral for stroke survivors, where a hand orthosis developed in our lab collects a set of biosignals from the patient and uses them to infer the activity that the patient intends to perform, so the orthosis can provide the right type of physical assistance at the right moment. My work develops machine learning algorithms that enable intent inferral with minimal data, including semi-supervised, meta-learning, and generative AI methods.

Jingxi Xu, Runsheng Wang, Siqi Shang et al.

Intent inferral on a hand orthosis for stroke patients is challenging due to the difficulty of data collection. Additionally, EMG signals exhibit significant variations across different conditions, sessions, and subjects, making it hard for classifiers to generalize. Traditional approaches require a large labeled dataset from the new condition, session, or subject to train intent classifiers; however, this data collection process is burdensome and time-consuming. In this paper, we propose ChatEMG, an autoregressive generative model that can generate synthetic EMG signals conditioned on prompts (i.e., a given sequence of EMG signals). ChatEMG enables us to collect only a small dataset from the new condition, session, or subject and expand it with synthetic samples conditioned on prompts from this new context. ChatEMG leverages a vast repository of previous data via generative training while still remaining context-specific via prompting. Our experiments show that these synthetic samples are classifier-agnostic and can improve intent inferral accuracy for different types of classifiers. We demonstrate that our complete approach can be integrated into a single patient session, including the use of the classifier for functional orthosis-assisted tasks. To the best of our knowledge, this is the first time an intent classifier trained partially on synthetic data has been deployed for functional control of an orthosis by a stroke survivor. Videos, source code, and additional information can be found at https://jxu.ai/chatemg.

Ava Chen, Lauren Winterbottom, Sangwoo Park et al.

We propose a dual-cable method of stabilizing the thumb in the context of a hand orthosis designed for individuals with upper extremity hemiparesis after stroke. This cable network adds opposition/reposition capabilities to the thumb, and increases the likelihood of forming a hand pose that can successfully manipulate objects. In addition to a passive-thumb version (where both cables are of fixed length), our approach also allows for a single-actuator active-thumb version (where the extension cable is actuated while the abductor remains passive), which allows a range of motion intended to facilitate creating and maintaining grasps. We performed experiments with five chronic stroke survivors consisting of unimanual resistive-pull tasks and bimanual twisting tasks with simulated real-world objects; these explored the effects of thumb assistance on grasp stability and functional range of motion. Our results show that both active- and passive-thumb versions achieved similar performance in terms of improving grasp force generation over a no-device baseline, but active thumb stabilization enabled users to maintain grasps for longer durations.

Jingxi Xu, Bruce Lee, Nikolai Matni et al.

The difficulty of optimal control problems has classically been characterized in terms of system properties such as minimum eigenvalues of controllability/observability gramians. We revisit these characterizations in the context of the increasing popularity of data-driven techniques like reinforcement learning (RL), and in control settings where input observations are high-dimensional images and transition dynamics are unknown. Specifically, we ask: to what extent are quantifiable control and perceptual difficulty metrics of a task predictive of the performance and sample complexity of data-driven controllers? We modulate two different types of partial observability in a cartpole "stick-balancing" problem -- (i) the height of one visible fixation point on the cartpole, which can be used to tune fundamental limits of performance achievable by any controller, and by (ii) the level of perception noise in the fixation point position inferred from depth or RGB images of the cartpole. In these settings, we empirically study two popular families of controllers: RL and system identification-based $H_\infty$ control, using visually estimated system state. Our results show that the fundamental limits of robust control have corresponding implications for the sample-efficiency and performance of learned perception-based controllers. Visit our project website https://jxu.ai/rl-vs-control-web for more information.

Jingxi Xu, Da Tang, Tony Jebara

The cost of annotating training data has traditionally been a bottleneck for supervised learning approaches. The problem is further exacerbated when supervised learning is applied to a number of correlated tasks simultaneously since the amount of labels required scales with the number of tasks. To mitigate this concern, we propose an active multitask learning algorithm that achieves knowledge transfer between tasks. The approach forms a so-called committee for each task that jointly makes decisions and directly shares data across similar tasks. Our approach reduces the number of queries needed during training while maintaining high accuracy on test data. Empirical results on benchmark datasets show significant improvements on both accuracy and number of query requests.

Iretiayo Akinola, Jingxi Xu, Shuran Song et al.

Grasping in dynamic environments presents a unique set of challenges. A stable and reachable grasp can become unreachable and unstable as the target object moves, motion planning needs to be adaptive and in real time, the delay in computation makes prediction necessary. In this paper, we present a dynamic grasping framework that is reachability-aware and motion-aware. Specifically, we model the reachability space of the robot using a signed distance field which enables us to quickly screen unreachable grasps. Also, we train a neural network to predict the grasp quality conditioned on the current motion of the target. Using these as ranking functions, we quickly filter a large grasp database to a few grasps in real time. In addition, we present a seeding approach for arm motion generation that utilizes solution from previous time step. This quickly generates a new arm trajectory that is close to the previous plan and prevents fluctuation. We implement a recurrent neural network (RNN) for modelling and predicting the object motion. Our extensive experiments demonstrate the importance of each of these components and we validate our pipeline on a real robot.

Huy Ha, Jingxi Xu, Shuran Song

We present a closed-loop multi-arm motion planner that is scalable and flexible with team size. Traditional multi-arm robot systems have relied on centralized motion planners, whose runtimes often scale exponentially with team size, and thus, fail to handle dynamic environments with open-loop control. In this paper, we tackle this problem with multi-agent reinforcement learning, where a decentralized policy is trained to control one robot arm in the multi-arm system to reach its target end-effector pose given observations of its workspace state and target end-effector pose. The policy is trained using Soft Actor-Critic with expert demonstrations from a sampling-based motion planning algorithm (i.e., BiRRT). By leveraging classical planning algorithms, we can improve the learning efficiency of the reinforcement learning algorithm while retaining the fast inference time of neural networks. The resulting policy scales sub-linearly and can be deployed on multi-arm systems with variable team sizes. Thanks to the closed-loop and decentralized formulation, our approach generalizes to 5-10 multi-arm systems and dynamic moving targets (>90% success rate for a 10-arm system), despite being trained on only 1-4 arm planning tasks with static targets. Code and data links can be found at https://multiarm.cs.columbia.edu.

Jingxi Xu, Cassie Meeker, Ava Chen et al.

In order to provide therapy in a functional context, controls for wearable robotic orthoses need to be robust and intuitive. We have previously introduced an intuitive, user-driven, EMG-based method to operate a robotic hand orthosis, but the process of training a control that is robust to concept drift (changes in the input signal) places a substantial burden on the user. In this paper, we explore semi-supervised learning as a paradigm for controlling a powered hand orthosis for stroke subjects. To the best of our knowledge, this is the first use of semi-supervised learning for an orthotic application. Specifically, we propose a disagreement-based semi-supervision algorithm for handling intrasession concept drift based on multimodal ipsilateral sensing. We evaluate the performance of our algorithm on data collected from five stroke subjects. Our results show that the proposed algorithm helps the device adapt to intrasession drift using unlabeled data and reduces the training burden placed on the user. We also validate the feasibility of our proposed algorithm with a functional task; in these experiments, two subjects successfully completed multiple instances of a pick-and-handover task.

Iretiayo Akinola, Zizhao Wang, Junyao Shi et al.

In reinforcement learning (RL), sparse rewards are a natural way to specify the task to be learned. However, most RL algorithms struggle to learn in this setting since the learning signal is mostly zeros. In contrast, humans are good at assessing and predicting the future consequences of actions and can serve as good reward/policy shapers to accelerate the robot learning process. Previous works have shown that the human brain generates an error-related signal, measurable using electroencephelography (EEG), when the human perceives the task being done erroneously. In this work, we propose a method that uses evaluative feedback obtained from human brain signals measured via scalp EEG to accelerate RL for robotic agents in sparse reward settings. As the robot learns the task, the EEG of a human observer watching the robot attempts is recorded and decoded into noisy error feedback signal. From this feedback, we use supervised learning to obtain a policy that subsequently augments the behavior policy and guides exploration in the early stages of RL. This bootstraps the RL learning process to enable learning from sparse reward. Using a robotic navigation task as a test bed, we show that our method achieves a stable obstacle-avoidance policy with high success rate, outperforming learning from sparse rewards only that struggles to achieve obstacle avoidance behavior or fails to advance to the goal.

David Watkins-Valls, Jingxi Xu, Nicholas Waytowich et al.

We present a robot navigation system that uses an imitation learning framework to successfully navigate in complex environments. Our framework takes a pre-built 3D scan of a real environment and trains an agent from pre-generated expert trajectories to navigate to any position given a panoramic view of the goal and the current visual input without relying on map, compass, odometry, or relative position of the target at runtime. Our end-to-end trained agent uses RGB and depth (RGBD) information and can handle large environments (up to $1031m^2$) across multiple rooms (up to $40$) and generalizes to unseen targets. We show that when compared to several baselines our method (1) requires fewer training examples and less training time, (2) reaches the goal location with higher accuracy, and (3) produces better solutions with shorter paths for long-range navigation tasks.