Yixuan Wang

Yixuan Wang, Mingtong Zhang, Zhuoran Li et al. · mit, stanford

Scene representation is a crucial design choice in robotic manipulation systems. An ideal representation is expected to be 3D, dynamic, and semantic to meet the demands of diverse manipulation tasks. However, previous works often lack all three properties simultaneously. In this work, we introduce D$^3$Fields -- dynamic 3D descriptor fields. These fields are implicit 3D representations that take in 3D points and output semantic features and instance masks. They can also capture the dynamics of the underlying 3D environments. Specifically, we project arbitrary 3D points in the workspace onto multi-view 2D visual observations and interpolate features derived from visual foundational models. The resulting fused descriptor fields allow for flexible goal specifications using 2D images with varied contexts, styles, and instances. To evaluate the effectiveness of these descriptor fields, we apply our representation to rearrangement tasks in a zero-shot manner. Through extensive evaluation in real worlds and simulations, we demonstrate that D$^3$Fields are effective for zero-shot generalizable rearrangement tasks. We also compare D$^3$Fields with state-of-the-art implicit 3D representations and show significant improvements in effectiveness and efficiency.

Yixuan Wang, Yunzhu Li, Katherine Driggs-Campbell et al. · mit, stanford

Dynamics models learned from visual observations have shown to be effective in various robotic manipulation tasks. One of the key questions for learning such dynamics models is what scene representation to use. Prior works typically assume representation at a fixed dimension or resolution, which may be inefficient for simple tasks and ineffective for more complicated tasks. In this work, we investigate how to learn dynamic and adaptive representations at different levels of abstraction to achieve the optimal trade-off between efficiency and effectiveness. Specifically, we construct dynamic-resolution particle representations of the environment and learn a unified dynamics model using graph neural networks (GNNs) that allows continuous selection of the abstraction level. During test time, the agent can adaptively determine the optimal resolution at each model-predictive control (MPC) step. We evaluate our method in object pile manipulation, a task we commonly encounter in cooking, agriculture, manufacturing, and pharmaceutical applications. Through comprehensive evaluations both in the simulation and the real world, we show that our method achieves significantly better performance than state-of-the-art fixed-resolution baselines at the gathering, sorting, and redistribution of granular object piles made with various instances like coffee beans, almonds, corn, etc.

Ruochen Jiao, Yixuan Wang, Xiangguo Liu et al. · berkeley

Trajectory generation and trajectory prediction are two critical tasks in autonomous driving, which generate various trajectories for testing during development and predict the trajectories of surrounding vehicles during operation, respectively. In recent years, emerging data-driven deep learning-based methods have shown great promise for these two tasks in learning various traffic scenarios and improving average performance without assuming physical models. However, it remains a challenging problem for these methods to ensure that the generated/predicted trajectories are physically realistic. This challenge arises because learning-based approaches often function as opaque black boxes and do not adhere to physical laws. Conversely, existing model-based methods provide physically feasible results but are constrained by predefined model structures, limiting their capabilities to address complex scenarios. To address the limitations of these two types of approaches, we propose a new method that integrates kinematic knowledge into neural stochastic differential equations (SDE) and designs a variational autoencoder based on this latent kinematics-aware SDE (LK-SDE) to generate vehicle motions. Experimental results demonstrate that our method significantly outperforms both model-based and learning-based baselines in producing physically realistic and precisely controllable vehicle trajectories. Additionally, it performs well in predicting unobservable physical variables in the latent space.

Yixuan Wang, Simon Sinong Zhan, Ruochen Jiao et al.

It is quite challenging to ensure the safety of reinforcement learning (RL) agents in an unknown and stochastic environment under hard constraints that require the system state not to reach certain specified unsafe regions. Many popular safe RL methods such as those based on the Constrained Markov Decision Process (CMDP) paradigm formulate safety violations in a cost function and try to constrain the expectation of cumulative cost under a threshold. However, it is often difficult to effectively capture and enforce hard reachability-based safety constraints indirectly with such constraints on safety violation costs. In this work, we leverage the notion of barrier function to explicitly encode the hard safety constraints, and given that the environment is unknown, relax them to our design of \emph{generative-model-based soft barrier functions}. Based on such soft barriers, we propose a safe RL approach that can jointly learn the environment and optimize the control policy, while effectively avoiding unsafe regions with safety probability optimization. Experiments on a set of examples demonstrate that our approach can effectively enforce hard safety constraints and significantly outperform CMDP-based baseline methods in system safe rate measured via simulations.

Yixuan Wang, Ruochen Jiao, Sinong Simon Zhan et al.

Autonomous Driving (AD) encounters significant safety hurdles in long-tail unforeseen driving scenarios, largely stemming from the non-interpretability and poor generalization of the deep neural networks within the AD system, particularly in out-of-distribution and uncertain data. To this end, this paper explores the integration of Large Language Models (LLMs) into AD systems, leveraging their robust common-sense knowledge and reasoning abilities. The proposed methodologies employ LLMs as intelligent decision-makers in behavioral planning, augmented with a safety verifier shield for contextual safety learning, for enhancing driving performance and safety. We present two key studies in a simulated environment: an adaptive LLM-conditioned Model Predictive Control (MPC) and an LLM-enabled interactive behavior planning scheme with a state machine. Demonstrating superior performance and safety metrics compared to state-of-the-art approaches, our approach shows the promising potential for using LLMs for autonomous vehicles.

Ziming Liu, Andrew M. Stuart, Yixuan Wang

We propose a sampling method based on an ensemble approximation of second order Langevin dynamics. The log target density is appended with a quadratic term in an auxiliary momentum variable and damped-driven Hamiltonian dynamics introduced; the resulting stochastic differential equation is invariant to the Gibbs measure, with marginal on the position coordinates given by the target. A preconditioner based on covariance under the law of the dynamics does not change this invariance property, and is introduced to accelerate convergence to the Gibbs measure. The resulting mean-field dynamics may be approximated by an ensemble method; this results in a gradient-free and affine-invariant stochastic dynamical system. Numerical results demonstrate its potential as the basis for a numerical sampler in Bayesian inverse problems.

Ziming Liu, Pingchuan Ma, Yixuan Wang et al.

A major challenge of AI + Science lies in their inherent incompatibility: today's AI is primarily based on connectionism, while science depends on symbolism. To bridge the two worlds, we propose a framework to seamlessly synergize Kolmogorov-Arnold Networks (KANs) and science. The framework highlights KANs' usage for three aspects of scientific discovery: identifying relevant features, revealing modular structures, and discovering symbolic formulas. The synergy is bidirectional: science to KAN (incorporating scientific knowledge into KANs), and KAN to science (extracting scientific insights from KANs). We highlight major new functionalities in the pykan package: (1) MultKAN: KANs with multiplication nodes. (2) kanpiler: a KAN compiler that compiles symbolic formulas into KANs. (3) tree converter: convert KANs (or any neural networks) to tree graphs. Based on these tools, we demonstrate KANs' capability to discover various types of physical laws, including conserved quantities, Lagrangians, symmetries, and constitutive laws.

Yixuan Wang, Weichao Zhou, Jiameng Fan et al.

Neural networks (NNs) playing the role of controllers have demonstrated impressive empirical performances on challenging control problems. However, the potential adoption of NN controllers in real-life applications also gives rise to a growing concern over the safety of these neural-network controlled systems (NNCSs), especially when used in safety-critical applications. In this work, we present POLAR-Express, an efficient and precise formal reachability analysis tool for verifying the safety of NNCSs. POLAR-Express uses Taylor model arithmetic to propagate Taylor models (TMs) across a neural network layer-by-layer to compute an overapproximation of the neural-network function. It can be applied to analyze any feed-forward neural network with continuous activation functions. We also present a novel approach to propagate TMs more efficiently and precisely across ReLU activation functions. In addition, POLAR-Express provides parallel computation support for the layer-by-layer propagation of TMs, thus significantly improving the efficiency and scalability over its earlier prototype POLAR. Across the comparison with six other state-of-the-art tools on a diverse set of benchmarks, POLAR-Express achieves the best verification efficiency and tightness in the reachable set analysis.

Zhilu Wang, Yixuan Wang, Feisi Fu et al.

With the increment of interest in leveraging machine learning technology in safety-critical systems, the robustness of neural networks under external disturbance receives more and more concerns. Global robustness is a robustness property defined on the entire input domain. And a certified globally robust network can ensure its robustness on any possible network input. However, the state-of-the-art global robustness certification algorithm can only certify networks with at most several thousand neurons. In this paper, we propose the GPU-supported global robustness certification framework GROCET, which is more efficient than the previous optimization-based certification approach. Moreover, GROCET provides differentiable global robustness, which is leveraged in the training of globally robust neural networks.

Simon Sinong Zhan, Yixuan Wang, Qingyuan Wu et al.

In the context of safe exploration, Reinforcement Learning (RL) has long grappled with the challenges of balancing the tradeoff between maximizing rewards and minimizing safety violations, particularly in complex environments with contact-rich or non-smooth dynamics, and when dealing with high-dimensional pixel observations. Furthermore, incorporating state-wise safety constraints in the exploration and learning process, where the agent must avoid unsafe regions without prior knowledge, adds another layer of complexity. In this paper, we propose a novel pixel-observation safe RL algorithm that efficiently encodes state-wise safety constraints with unknown hazard regions through a newly introduced latent barrier-like function learning mechanism. As a joint learning framework, our approach begins by constructing a latent dynamics model with low-dimensional latent spaces derived from pixel observations. We then build and learn a latent barrier-like function on top of the latent dynamics and conduct policy optimization simultaneously, thereby improving both safety and the total expected return. Experimental evaluations on the safety-gym benchmark suite demonstrate that our proposed method significantly reduces safety violations throughout the training process, and demonstrates faster safety convergence compared to existing methods while achieving competitive results in reward return.

Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang et al.

Reinforcement learning (RL) is challenging in the common case of delays between events and their sensory perceptions. State-of-the-art (SOTA) state augmentation techniques either suffer from state space explosion or performance degeneration in stochastic environments. To address these challenges, we present a novel Auxiliary-Delayed Reinforcement Learning (AD-RL) method that leverages auxiliary tasks involving short delays to accelerate RL with long delays, without compromising performance in stochastic environments. Specifically, AD-RL learns a value function for short delays and uses bootstrapping and policy improvement techniques to adjust it for long delays. We theoretically show that this can greatly reduce the sample complexity. On deterministic and stochastic benchmarks, our method significantly outperforms the SOTAs in both sample efficiency and policy performance. Code is available at https://github.com/QingyuanWuNothing/AD-RL.

Qingyuan Wu, Simon Sinong Zhan, Yixuan Wang et al.

In environments with delayed observation, state augmentation by including actions within the delay window is adopted to retrieve Markovian property to enable reinforcement learning (RL). However, state-of-the-art (SOTA) RL techniques with Temporal-Difference (TD) learning frameworks often suffer from learning inefficiency, due to the significant expansion of the augmented state space with the delay. To improve learning efficiency without sacrificing performance, this work introduces a novel framework called Variational Delayed Policy Optimization (VDPO), which reformulates delayed RL as a variational inference problem. This problem is further modelled as a two-step iterative optimization problem, where the first step is TD learning in the delay-free environment with a small state space, and the second step is behaviour cloning which can be addressed much more efficiently than TD learning. We not only provide a theoretical analysis of VDPO in terms of sample complexity and performance, but also empirically demonstrate that VDPO can achieve consistent performance with SOTA methods, with a significant enhancement of sample efficiency (approximately 50\% less amount of samples) in the MuJoCo benchmark.

Yixuan Wang, Baoxin Wang, Yijun Liu et al.

Over-correction is a critical problem in Chinese grammatical error correction (CGEC) task. Recent work using model ensemble methods based on voting can effectively mitigate over-correction and improve the precision of the GEC system. However, these methods still require the output of several GEC systems and inevitably lead to reduced error recall. In this light, we propose the LM-Combiner, a rewriting model that can directly modify the over-correction of GEC system outputs without a model ensemble. Specifically, we train the model on an over-correction dataset constructed through the proposed K-fold cross inference method, which allows it to directly generate filtered sentences by combining the original and the over-corrected text. In the inference stage, we directly take the original sentences and the output results of other systems as input and then obtain the filtered sentences through LM-Combiner. Experiments on the FCGEC dataset show that our proposed method effectively alleviates the over-correction of the original system (+18.2 Precision) while ensuring the error recall remains unchanged. Besides, we find that LM-Combiner still has a good rewriting performance even with small parameters and few training data, and thus can cost-effectively mitigate the over-correction of black-box GEC systems (e.g., ChatGPT).

Yixuan Wang, Leonor Fermoselle, Tarik Kelestemur et al.

Mobile exploration is a longstanding challenge in robotics, yet current methods primarily focus on active perception instead of active interaction, limiting the robot's ability to interact with and fully explore its environment. Existing robotic exploration approaches via active interaction are often restricted to tabletop scenes, neglecting the unique challenges posed by mobile exploration, such as large exploration spaces, complex action spaces, and diverse object relations. In this work, we introduce a 3D relational object graph that encodes diverse object relations and enables exploration through active interaction. We develop a system based on this representation and evaluate it across diverse scenes. Our qualitative and quantitative results demonstrate the system's effectiveness and generalization capabilities, outperforming methods that rely solely on vision-language models (VLMs).

Guanjun Wang, Lu Wang, Ning Niu et al.

Sclera segmentation is crucial for developing automatic eye-related medical computer-aided diagnostic systems, as well as for personal identification and verification, because the sclera contains distinct personal features. Deep learning-based sclera segmentation has achieved significant success compared to traditional methods that rely on hand-crafted features, primarily because it can autonomously extract critical output-related features without the need to consider potential physical constraints. However, achieving accurate sclera segmentation using these methods is challenging due to the scarcity of high-quality, fully labeled datasets, which depend on costly, labor-intensive medical acquisition and expertise. To address this challenge, this paper introduces a novel sclera segmentation framework that excels with limited labeled samples. Specifically, we employ a semi-supervised learning method that integrates domain-specific improvements and image-based spatial transformations to enhance segmentation performance. Additionally, we have developed a real-world eye diagnosis dataset to enrich the evaluation process. Extensive experiments on our dataset and two additional public datasets demonstrate the effectiveness and superiority of our proposed method, especially with significantly fewer labeled samples.

Simon Sinong Zhan, Qingyuan Wu, Zhian Ruan et al.

Inverse Reinforcement Learning (IRL) has demonstrated effectiveness in a variety of imitation tasks. In this paper, we introduce an IRL framework designed to extract rewarding features from expert trajectories affected by delayed disturbances. Instead of relying on direct observations, our approach employs an efficient off-policy adversarial training framework to derive expert features and recover optimal policies from augmented delayed observations. Empirical evaluations in the MuJoCo environment under diverse delay settings validate the effectiveness of our method. Furthermore, we provide a theoretical analysis showing that recovering expert policies from augmented delayed observations outperforms using direct delayed observations.

Yixuan Wang, Simon Zhan, Zhilu Wang et al.

In model-based reinforcement learning for safety-critical control systems, it is important to formally certify system properties (e.g., safety, stability) under the learned controller. However, as existing methods typically apply formal verification \emph{after} the controller has been learned, it is sometimes difficult to obtain any certificate, even after many iterations between learning and verification. To address this challenge, we propose a framework that jointly conducts reinforcement learning and formal verification by formulating and solving a novel bilevel optimization problem, which is differentiable by the gradients from the value function and certificates. Experiments on a variety of examples demonstrate the significant advantages of our framework over the model-based stochastic value gradient (SVG) method and the model-free proximal policy optimization (PPO) method in finding feasible controllers with barrier functions and Lyapunov functions that ensure system safety and stability.

Xiangguo Liu, Chao Huang, Yixuan Wang et al.

Neural networks have shown great promises in planning, control, and general decision making for learning-enabled cyber-physical systems (LE-CPSs), especially in improving performance under complex scenarios. However, it is very challenging to formally analyze the behavior of neural network based planners for ensuring system safety, which significantly impedes their applications in safety-critical domains such as autonomous driving. In this work, we propose a hierarchical neural network based planner that analyzes the underlying physical scenarios of the system and learns a system-level behavior planning scheme with multiple scenario-specific motion-planning strategies. We then develop an efficient verification method that incorporates overapproximation of the system state reachable set and novel partition and union techniques for formally ensuring system safety under our physics-aware planner. With theoretical analysis, we show that considering the different physical scenarios and building a hierarchical planner based on such analysis may improve system safety and verifiability. We also empirically demonstrate the effectiveness of our approach and its advantage over other baselines in practical case studies of unprotected left turn and highway merging, two common challenging safety-critical tasks in autonomous driving.

Shichao Xu, Yangyang Fu, Yixuan Wang et al.

As people spend up to 87% of their time indoors, intelligent Heating, Ventilation, and Air Conditioning (HVAC) systems in buildings are essential for maintaining occupant comfort and reducing energy consumption. These HVAC systems in smart buildings rely on real-time sensor readings, which in practice often suffer from various faults and could also be vulnerable to malicious attacks. Such faulty sensor inputs may lead to the violation of indoor environment requirements (e.g., temperature, humidity, etc.) and the increase of energy consumption. While many model-based approaches have been proposed in the literature for building HVAC control, it is costly to develop accurate physical models for ensuring their performance and even more challenging to address the impact of sensor faults. In this work, we present a novel learning-based framework for sensor fault-tolerant HVAC control, which includes three deep learning based components for 1) generating temperature proposals with the consideration of possible sensor faults, 2) selecting one of the proposals based on the assessment of their accuracy, and 3) applying reinforcement learning with the selected temperature proposal. Moreover, to address the challenge of training data insufficiency in building-related tasks, we propose a model-assisted learning method leveraging an abstract model of building physical dynamics. Through extensive experiments, we demonstrate that the proposed fault-tolerant HVAC control framework can significantly reduce building temperature violations under a variety of sensor fault patterns while maintaining energy efficiency.

Shichao Xu, Lixu Wang, Yixuan Wang et al.

Data quantity and quality are crucial factors for data-driven learning methods. In some target problem domains, there are not many data samples available, which could significantly hinder the learning process. While data from similar domains may be leveraged to help through domain adaptation, obtaining high-quality labeled data for those source domains themselves could be difficult or costly. To address such challenges on data insufficiency for classification problem in a target domain, we propose a weak adaptation learning (WAL) approach that leverages unlabeled data from a similar source domain, a low-cost weak annotator that produces labels based on task-specific heuristics, labeling rules, or other methods (albeit with inaccuracy), and a small amount of labeled data in the target domain. Our approach first conducts a theoretical analysis on the error bound of the trained classifier with respect to the data quantity and the performance of the weak annotator, and then introduces a multi-stage weak adaptation learning method to learn an accurate classifier by lowering the error bound. Our experiments demonstrate the effectiveness of our approach in learning an accurate classifier with limited labeled data in the target domain and unlabeled data in the source domain.

Shichao Xu, Yixuan Wang, Yanzhi Wang et al.

The design of building heating, ventilation, and air conditioning (HVAC) system is critically important, as it accounts for around half of building energy consumption and directly affects occupant comfort, productivity, and health. Traditional HVAC control methods are typically based on creating explicit physical models for building thermal dynamics, which often require significant effort to develop and are difficult to achieve sufficient accuracy and efficiency for runtime building control and scalability for field implementations. Recently, deep reinforcement learning (DRL) has emerged as a promising data-driven method that provides good control performance without analyzing physical models at runtime. However, a major challenge to DRL (and many other data-driven learning methods) is the long training time it takes to reach the desired performance. In this work, we present a novel transfer learning based approach to overcome this challenge. Our approach can effectively transfer a DRL-based HVAC controller trained for the source building to a controller for the target building with minimal effort and improved performance, by decomposing the design of neural network controller into a transferable front-end network that captures building-agnostic behavior and a back-end network that can be efficiently trained for each specific building. We conducted experiments on a variety of transfer scenarios between buildings with different sizes, numbers of thermal zones, materials and layouts, air conditioner types, and ambient weather conditions. The experimental results demonstrated the effectiveness of our approach in significantly reducing the training time, energy cost, and temperature violations.

Ziming Liu, Sitian Qian, Yixuan Wang et al.

Principal component analysis (PCA) has achieved great success in unsupervised learning by identifying covariance correlations among features. If the data collection fails to capture the covariance information, PCA will not be able to discover meaningful modes. In particular, PCA will fail the spatial Gaussian Process (GP) model in the undersampling regime, i.e. the averaged distance of neighboring anchor points (spatial features) is greater than the correlation length of GP. Counterintuitively, by drawing the connection between PCA and Schrödinger equation, we can not only attack the undersampling challenge but also compute in an efficient and decoupled way with the proposed algorithm called Schrödinger PCA. Our algorithm only requires variances of features and estimated correlation length as input, constructs the corresponding Schrödinger equation, and solves it to obtain the energy eigenstates, which coincide with principal components. We will also establish the connection of our algorithm to the model reduction techniques in the partial differential equation (PDE) community, where the steady-state Schrödinger operator is identified as a second-order approximation to the covariance function. Numerical experiments are implemented to testify the validity and efficiency of the proposed algorithm, showing its potential for unsupervised learning tasks on general graphs and manifolds.