Shiqi Liu

Yihang Yao, Zhepeng Cen, Wenhao Ding et al. · cmu

Offline safe reinforcement learning (RL) aims to train a policy that satisfies constraints using a pre-collected dataset. Most current methods struggle with the mismatch between imperfect demonstrations and the desired safe and rewarding performance. In this paper, we introduce OASIS (cOnditionAl diStributIon Shaping), a new paradigm in offline safe RL designed to overcome these critical limitations. OASIS utilizes a conditional diffusion model to synthesize offline datasets, thus shaping the data distribution toward a beneficial target domain. Our approach makes compliance with safety constraints through effective data utilization and regularization techniques to benefit offline safe RL training. Comprehensive evaluations on public benchmarks and varying datasets showcase OASIS's superiority in benefiting offline safe RL agents to achieve high-reward behavior while satisfying the safety constraints, outperforming established baselines. Furthermore, OASIS exhibits high data efficiency and robustness, making it suitable for real-world applications, particularly in tasks where safety is imperative and high-quality demonstrations are scarce.

Shiqi Liu, Mengdi Xu, Piede Huang et al.

Continual reinforcement learning aims to sequentially learn a variety of tasks, retaining the ability to perform previously encountered tasks while simultaneously developing new policies for novel tasks. However, current continual RL approaches overlook the fact that certain tasks are identical under basic group operations like rotations or translations, especially with visual inputs. They may unnecessarily learn and maintain a new policy for each similar task, leading to poor sample efficiency and weak generalization capability. To address this, we introduce a unique Continual Vision-based Reinforcement Learning method that recognizes Group Symmetries, called COVERS, cultivating a policy for each group of equivalent tasks rather than individual tasks. COVERS employs a proximal policy optimization-based RL algorithm with an equivariant feature extractor and a novel task grouping mechanism that relies on the extracted invariant features. We evaluate COVERS on sequences of table-top manipulation tasks that incorporate image observations and robot proprioceptive information in both simulations and on real robot platforms. Our results show that COVERS accurately assigns tasks to their respective groups and significantly outperforms existing methods in terms of generalization capability.

Mengdi Xu, Peide Huang, Wenhao Yu et al.

Tool use is a hallmark of advanced intelligence, exemplified in both animal behavior and robotic capabilities. This paper investigates the feasibility of imbuing robots with the ability to creatively use tools in tasks that involve implicit physical constraints and long-term planning. Leveraging Large Language Models (LLMs), we develop RoboTool, a system that accepts natural language instructions and outputs executable code for controlling robots in both simulated and real-world environments. RoboTool incorporates four pivotal components: (i) an "Analyzer" that interprets natural language to discern key task-related concepts, (ii) a "Planner" that generates comprehensive strategies based on the language input and key concepts, (iii) a "Calculator" that computes parameters for each skill, and (iv) a "Coder" that translates these plans into executable Python code. Our results show that RoboTool can not only comprehend explicit or implicit physical constraints and environmental factors but also demonstrate creative tool use. Unlike traditional Task and Motion Planning (TAMP) methods that rely on explicit optimization, our LLM-based system offers a more flexible, efficient, and user-friendly solution for complex robotics tasks. Through extensive experiments, we validate that RoboTool is proficient in handling tasks that would otherwise be infeasible without the creative use of tools, thereby expanding the capabilities of robotic systems. Demos are available on our project page: https://creative-robotool.github.io/.

Shiqi Liu

Generalization is at the core of machine learning models. However, the definition of generalization is not entirely clear. We employ set theory to introduce the concepts of algorithms, hypotheses, and dataset generalization. We analyze the properties of dataset generalization and prove a theorem on surrogate generalization procedures. This theorem leads to our generalization method. Through a generalization experiment on the MNIST dataset, we obtain 13,541 sample bases. When we use the entire training set to evaluate the model's performance, the models achieve an accuracy of 99.945%. However, if we shift the sample bases or modify the neural network structure, the performance experiences a significant decline. We also identify consistently mispredicted samples and find that they are all challenging examples. The experiments substantiated the accuracy of the generalization definition and the effectiveness of the proposed methods. Both the set-theoretic deduction and the experiments help us better understand generalization.

Zijie Zeng, Shiqi Liu, Lele Sha et al.

This study explores the challenge of sentence-level AI-generated text detection within human-AI collaborative hybrid texts. Existing studies of AI-generated text detection for hybrid texts often rely on synthetic datasets. These typically involve hybrid texts with a limited number of boundaries. We contend that studies of detecting AI-generated content within hybrid texts should cover different types of hybrid texts generated in realistic settings to better inform real-world applications. Therefore, our study utilizes the CoAuthor dataset, which includes diverse, realistic hybrid texts generated through the collaboration between human writers and an intelligent writing system in multi-turn interactions. We adopt a two-step, segmentation-based pipeline: (i) detect segments within a given hybrid text where each segment contains sentences of consistent authorship, and (ii) classify the authorship of each identified segment. Our empirical findings highlight (1) detecting AI-generated sentences in hybrid texts is overall a challenging task because (1.1) human writers' selecting and even editing AI-generated sentences based on personal preferences adds difficulty in identifying the authorship of segments; (1.2) the frequent change of authorship between neighboring sentences within the hybrid text creates difficulties for segment detectors in identifying authorship-consistent segments; (1.3) the short length of text segments within hybrid texts provides limited stylistic cues for reliable authorship determination; (2) before embarking on the detection process, it is beneficial to assess the average length of segments within the hybrid text. This assessment aids in deciding whether (2.1) to employ a text segmentation-based strategy for hybrid texts with longer segments, or (2.2) to adopt a direct sentence-by-sentence classification strategy for those with shorter segments.

Xilun Zhang, Shiqi Liu, Peide Huang et al. · cmu

Sim-to-real transfer remains a significant challenge in robotics due to the discrepancies between simulated and real-world dynamics. Traditional methods like Domain Randomization often fail to capture fine-grained dynamics, limiting their effectiveness for precise control tasks. In this work, we propose a novel approach that dynamically adjusts simulation environment parameters online using in-context learning. By leveraging past interaction histories as context, our method adapts the simulation environment dynamics to real-world dynamics without requiring gradient updates, resulting in faster and more accurate alignment between simulated and real-world performance. We validate our approach across two tasks: object scooping and table air hockey. In the sim-to-sim evaluations, our method significantly outperforms the baselines on environment parameter estimation by 80% and 42% in the object scooping and table air hockey setups, respectively. Furthermore, our method achieves at least 70% success rate in sim-to-real transfer on object scooping across three different objects. By incorporating historical interaction data, our approach delivers efficient and smooth system identification, advancing the deployment of robots in dynamic real-world scenarios. Demos are available on our project page: https://sim2real-capture.github.io/

Guoyou Wang, Yihua Tan, Shiqi Liu

Taylor's formula holds significant importance in function representation, such as solving differential difference equations, ordinary differential equations, partial differential equations, and further promotes applications in visual perception, complex control, fluid mechanics, weather forecasting and thermodynamics. However, the Taylor's formula suffers from the curse of dimensionality and error propagation during derivative computation in discrete situations. In this paper, we propose a new discrete differential operator to estimate derivatives and to represent continuous smooth function locally using the Vandermonde coefficient matrix derived from truncated Taylor series. Our method simultaneously computes all derivatives of orders less than the number of sample points, inherently mitigating error propagation. Utilizing equidistant uniform sampling, it achieves high-order accuracy while alleviating the curse of dimensionality. We mathematically establish rigorous error bounds for both derivative estimation and function representation, demonstrating tighter bounds for lower-order derivatives. We extend our method to the two-dimensional case, enabling its use for multivariate derivative calculations. Experiments demonstrate the effectiveness and superiority of the proposed method compared to the finite forward difference method for derivative estimation and cubic spline and linear interpolation for function representation. Consequently, our technique offers broad applicability across domains such as vision representation, feature extraction, fluid mechanics, and cross-media imaging.

Ziang Zheng, Guojian Zhan, Shiqi Liu et al.

Reinforcement learning (RL) has shown great potential in enabling quadruped robots to perform agile locomotion. However, directly training policies to simultaneously handle dual extreme challenges, i.e., extreme underactuation and extreme terrains, as in monopedal hopping tasks, remains highly challenging due to unstable early-stage interactions and unreliable reward feedback. To address this, we propose JumpER (jump-start reinforcement learning via self-evolving priors), an RL training framework that structures policy learning into multiple stages of increasing complexity. By dynamically generating self-evolving priors through iterative bootstrapping of previously learned policies, JumpER progressively refines and enhances guidance, thereby stabilizing exploration and policy optimization without relying on external expert priors or handcrafted reward shaping. Specifically, when integrated with a structured three-stage curriculum that incrementally evolves action modality, observation space, and task objective, JumpER enables quadruped robots to achieve robust monopedal hopping on unpredictable terrains for the first time. Remarkably, the resulting policy effectively handles challenging scenarios that traditional methods struggle to conquer, including wide gaps up to 60 cm, irregularly spaced stairs, and stepping stones with distances varying from 15 cm to 35 cm. JumpER thus provides a principled and scalable approach for addressing locomotion tasks under the dual challenges of extreme underactuation and extreme terrains.

Shiqi Liu, Wenhan Cao, Chang Liu et al.

Multi-object tracking (MOT) is an essential technique for navigation in autonomous driving. In tracking-by-detection systems, biases, false positives, and misses, which are referred to as outliers, are inevitable due to complex traffic scenarios. Recent tracking methods are based on filtering algorithms that overlook these outliers, leading to reduced tracking accuracy or even loss of the objects trajectory. To handle this challenge, we adopt a probabilistic perspective, regarding the generation of outliers as misspecification between the actual distribution of measurement data and the nominal measurement model used for filtering. We further demonstrate that, by designing a convolutional operation, we can mitigate this misspecification. Incorporating this operation into the widely used unscented Kalman filter (UKF) in commonly adopted tracking algorithms, we derive a variant of the UKF that is robust to outliers, called the convolutional UKF (ConvUKF). We show that ConvUKF maintains the Gaussian conjugate property, thus allowing for real-time tracking. We also prove that ConvUKF has a bounded tracking error in the presence of outliers, which implies robust stability. The experimental results on the KITTI and nuScenes datasets show improved accuracy compared to representative baseline algorithms for MOT tasks.

Shiqi Liu, Jie Lian, Xuchen Zhan et al.

Relative radiometric normalization (RRN) mosaicking among multiple remote sensing images is crucial for the downstream tasks, including map-making, image recognition, semantic segmentation, and change detection. However, there are often seam lines on the mosaic boundary and radiometric contrast left, especially in complex scenarios, making the appearance of mosaic images unsightly and reducing the accuracy of the latter classification/recognition algorithms. This paper renders a novel automatical approach to eliminate seam lines in complex RRN mosaicking scenarios. It utilizes the histogram matching on the overlap area to alleviate radiometric contrast, Poisson editing to remove the seam lines, and merging procedure to determine the normalization transfer order. Our method can handle the mosaicking seam lines with arbitrary shapes and images with extreme topological relationships (with a small intersection area). These conditions make the main feathering or blending methods, e.g., linear weighted blending and Laplacian pyramid blending, unavailable. In the experiment, our approach visually surpasses the automatic methods without Poisson editing and the manual blurring and feathering method using GIMP software.

Shiqi Liu, Jingxin Liu, Qian Zhao et al.

In the field of machine learning, it is still a critical issue to identify and supervise the learned representation without manually intervening or intuition assistance to extract useful knowledge or serve for the downstream tasks. In this work, we focus on supervising the influential factors extracted by the variational autoencoder(VAE). The VAE is proposed to learn independent low dimension representation while facing the problem that sometimes pre-set factors are ignored. We argue that the mutual information of the input and each learned factor of the representation plays a necessary indicator of discovering the influential factors. We find the VAE objective inclines to induce mutual information sparsity in factor dimension over the data intrinsic dimension and therefore result in some non-influential factors whose function on data reconstruction could be ignored. We show mutual information also influences the lower bound of the VAE's reconstruction error and downstream classification task. To make such indicator applicable, we design an algorithm for calculating the mutual information for the VAE and prove its consistency. Experimental results on MNIST, CelebA and DEAP datasets show that mutual information can help determine influential factors, of which some are interpretable and can be used to further generation and classification tasks, and help discover the variant that connects with emotion on DEAP dataset.

Shiqi Liu, Zilu Ma, Deyu Meng

By simulating the easy-to-hard learning manners of humans/animals, the learning regimes called curriculum learning~(CL) and self-paced learning~(SPL) have been recently investigated and invoked broad interests. However, the intrinsic mechanism for analyzing why such learning regimes can work has not been comprehensively investigated. To this issue, this paper proposes a concave conjugacy theory for looking into the insight of CL/SPL. Specifically, by using this theory, we prove the equivalence of the SPL regime and a latent concave objective, which is closely related to the known non-convex regularized penalty widely used in statistics and machine learning. Beyond the previous theory for explaining CL/SPL insights, this new theoretical framework on one hand facilitates two direct approaches for designing new SPL models for certain tasks, and on the other hand can help conduct the latent objective of self-paced curriculum learning, which is the advanced version of both CL/SPL and possess advantages of both learning regimes to a certain extent. This further facilitates a theoretical understanding for SPCL, instead of only CL/SPL as conventional. Under this theory, we attempt to attain intrinsic latent objectives of two curriculum forms, the partial order and group curriculums, which easily follow the theoretical understanding of the corresponding SPCL regimes.

Zilu Ma, Shiqi Liu, Deyu Meng

Self-paced learning (SPL) is a new methodology that simulates the learning principle of humans/animals to start learning easier aspects of a learning task, and then gradually take more complex examples into training. This new-coming learning regime has been empirically substantiated to be effective in various computer vision and pattern recognition tasks. Recently, it has been proved that the SPL regime has a close relationship to a implicit self-paced objective function. While this implicit objective could provide helpful interpretations to the effectiveness, especially the robustness, insights under the SPL paradigms, there are still no theoretical results strictly proved to verify such relationship. To this issue, in this paper, we provide some convergence results on this implicit objective of SPL. Specifically, we prove that the learning process of SPL always converges to critical points of this implicit objective under some mild conditions. This result verifies the intrinsic relationship between SPL and this implicit objective, and makes the previous robustness analysis on SPL complete and theoretically rational.