Xingyu Lin

Xingyu Lin, John So, Sashwat Mahalingam et al.

The existing internet-scale image and video datasets cover a wide range of everyday objects and tasks, bringing the potential of learning policies that generalize in diverse scenarios. Prior works have explored visual pre-training with different self-supervised objectives. Still, the generalization capabilities of the learned policies and the advantages over well-tuned baselines remain unclear from prior studies. In this work, we present a focused study of the generalization capabilities of the pre-trained visual representations at the categorical level. We identify the key bottleneck in using a frozen pre-trained visual backbone for policy learning and then propose SpawnNet, a novel two-stream architecture that learns to fuse pre-trained multi-layer representations into a separate network to learn a robust policy. Through extensive simulated and real experiments, we show significantly better categorical generalization compared to prior approaches in imitation learning settings. Open-sourced code and videos can be found on our website: https://xingyu-lin.github.io/spawnnet.

Zixuan Huang, Xingyu Lin, David Held · cmu

Self-occlusion is challenging for cloth manipulation, as it makes it difficult to estimate the full state of the cloth. Ideally, a robot trying to unfold a crumpled or folded cloth should be able to reason about the cloth's occluded regions. We leverage recent advances in pose estimation for cloth to build a system that uses explicit occlusion reasoning to unfold a crumpled cloth. Specifically, we first learn a model to reconstruct the mesh of the cloth. However, the model will likely have errors due to the complexities of the cloth configurations and due to ambiguities from occlusions. Our main insight is that we can further refine the predicted reconstruction by performing test-time finetuning with self-supervised losses. The obtained reconstructed mesh allows us to use a mesh-based dynamics model for planning while reasoning about occlusions. We evaluate our system both on cloth flattening as well as on cloth canonicalization, in which the objective is to manipulate the cloth into a canonical pose. Our experiments show that our method significantly outperforms prior methods that do not explicitly account for occlusions or perform test-time optimization. Videos and visualizations can be found on our $\href{https://sites.google.com/view/occlusion-reason/home}{\text{project website}}.$

Gautham Narayan Narasimhan, Kai Zhang, Ben Eisner et al. · cmu

Liquid state estimation is important for robotics tasks such as pouring; however, estimating the state of transparent liquids is a challenging problem. We propose a novel segmentation pipeline that can segment transparent liquids such as water from a static, RGB image without requiring any manual annotations or heating of the liquid for training. Instead, we use a generative model that is capable of translating images of colored liquids into synthetically generated transparent liquid images, trained only on an unpaired dataset of colored and transparent liquid images. Segmentation labels of colored liquids are obtained automatically using background subtraction. Our experiments show that we are able to accurately predict a segmentation mask for transparent liquids without requiring any manual annotations. We demonstrate the utility of transparent liquid segmentation in a robotic pouring task that controls pouring by perceiving the liquid height in a transparent cup. Accompanying video and supplementary materials can be found

Zixuan Huang, Xingyu Lin, David Held · cmu

State estimation is one of the greatest challenges for cloth manipulation due to cloth's high dimensionality and self-occlusion. Prior works propose to identify the full state of crumpled clothes by training a mesh reconstruction model in simulation. However, such models are prone to suffer from a sim-to-real gap due to differences between cloth simulation and the real world. In this work, we propose a self-supervised method to finetune a mesh reconstruction model in the real world. Since the full mesh of crumpled cloth is difficult to obtain in the real world, we design a special data collection scheme and an action-conditioned model-based cloth tracking method to generate pseudo-labels for self-supervised learning. By finetuning the pretrained mesh reconstruction model on this pseudo-labeled dataset, we show that we can improve the quality of the reconstructed mesh without requiring human annotations, and improve the performance of downstream manipulation task.

Xingyu Lin, Carl Qi, Yunchu Zhang et al.

Effective planning of long-horizon deformable object manipulation requires suitable abstractions at both the spatial and temporal levels. Previous methods typically either focus on short-horizon tasks or make strong assumptions that full-state information is available, which prevents their use on deformable objects. In this paper, we propose PlAnning with Spatial-Temporal Abstraction (PASTA), which incorporates both spatial abstraction (reasoning about objects and their relations to each other) and temporal abstraction (reasoning over skills instead of low-level actions). Our framework maps high-dimension 3D observations such as point clouds into a set of latent vectors and plans over skill sequences on top of the latent set representation. We show that our method can effectively perform challenging sequential deformable object manipulation tasks in the real world, which require combining multiple tool-use skills such as cutting with a knife, pushing with a pusher, and spreading the dough with a roller.

Carmelo Sferrazza, Dun-Ming Huang, Xingyu Lin et al.

Humanoid robots hold great promise in assisting humans in diverse environments and tasks, due to their flexibility and adaptability leveraging human-like morphology. However, research in humanoid robots is often bottlenecked by the costly and fragile hardware setups. To accelerate algorithmic research in humanoid robots, we present a high-dimensional, simulated robot learning benchmark, HumanoidBench, featuring a humanoid robot equipped with dexterous hands and a variety of challenging whole-body manipulation and locomotion tasks. Our findings reveal that state-of-the-art reinforcement learning algorithms struggle with most tasks, whereas a hierarchical learning approach achieves superior performance when supported by robust low-level policies, such as walking or reaching. With HumanoidBench, we provide the robotics community with a platform to identify the challenges arising when solving diverse tasks with humanoid robots, facilitating prompt verification of algorithms and ideas. The open-source code is available at https://humanoid-bench.github.io.

Carl Qi, Yilin Wu, Lifan Yu et al.

Autonomous systems that efficiently utilize tools can assist humans in completing many common tasks such as cooking and cleaning. However, current systems fall short of matching human-level of intelligence in terms of adapting to novel tools. Prior works based on affordance often make strong assumptions about the environments and cannot scale to more complex, contact-rich tasks. In this work, we tackle this challenge and explore how agents can learn to use previously unseen tools to manipulate deformable objects. We propose to learn a generative model of the tool-use trajectories as a sequence of tool point clouds, which generalizes to different tool shapes. Given any novel tool, we first generate a tool-use trajectory and then optimize the sequence of tool poses to align with the generated trajectory. We train a single model on four different challenging deformable object manipulation tasks, using demonstration data from only one tool per task. The model generalizes to various novel tools, significantly outperforming baselines. We further test our trained policy in the real world with unseen tools, where it achieves the performance comparable to human. Additional materials can be found on our project website: https://sites.google.com/view/toolgen.

Chuan Wen, Xingyu Lin, John So et al.

Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning. However, the high cost of collecting demonstration data is a significant bottleneck. Videos, as a rich data source, contain knowledge of behaviors, physics, and semantics, but extracting control-specific information from them is challenging due to the lack of action labels. In this work, we introduce a novel framework, Any-point Trajectory Modeling (ATM), that utilizes video demonstrations by pre-training a trajectory model to predict future trajectories of arbitrary points within a video frame. Once trained, these trajectories provide detailed control guidance, enabling the learning of robust visuomotor policies with minimal action-labeled data. Across over 130 language-conditioned tasks we evaluated in both simulation and the real world, ATM outperforms strong video pre-training baselines by 80% on average. Furthermore, we show effective transfer learning of manipulation skills from human videos and videos from a different robot morphology. Visualizations and code are available at: \url{https://xingyu-lin.github.io/atm}.

Xingyu Lin, Yufei Wang, Jake Olkin et al.

Manipulating deformable objects has long been a challenge in robotics due to its high dimensional state representation and complex dynamics. Recent success in deep reinforcement learning provides a promising direction for learning to manipulate deformable objects with data driven methods. However, existing reinforcement learning benchmarks only cover tasks with direct state observability and simple low-dimensional dynamics or with relatively simple image-based environments, such as those with rigid objects. In this paper, we present SoftGym, a set of open-source simulated benchmarks for manipulating deformable objects, with a standard OpenAI Gym API and a Python interface for creating new environments. Our benchmark will enable reproducible research in this important area. Further, we evaluate a variety of algorithms on these tasks and highlight challenges for reinforcement learning algorithms, including dealing with a state representation that has a high intrinsic dimensionality and is partially observable. The experiments and analysis indicate the strengths and limitations of existing methods in the context of deformable object manipulation that can help point the way forward for future methods development. Code and videos of the learned policies can be found on our project website.

Xingyu Lin, Yilin Wen, Du Su et al.

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly in their mathemat ical reasoning performance. However, GRPO and related entropy regularization methods still struggle with token-level sparse-rewards, which is an inherent chal lenge in chain-of-thought (CoT) reasoning. These approaches often rely on undifferen tiated token-level entropy regularization, which easily leads to entropy collapse or model degradation under sparse token rewards. In this work, we propose TEPO, a novel token-level framework that (1) leverages sequence-level likelihood to link group-level rewards with individual tokens via token-level aggregation, and (2) introduces a token-level KL-Divergence mask constraint that targets tokens with positive advantages and decreasing entropy to mitigate abrupt policy updates. Experiments demonstrate that TEPO not only achieves state-of-the-art performance on mathematical reasoning benchmarks but also markedly enhances training stability, reducing convergence time by 50% compared with GRPO/DAPO.

Xingyu Lin, Yilin Wen, En Wang et al.

Group Relative Policy Optimization (GRPO) has significantly advanced the reasoning ability of large language models (LLMs), particularly by boosting their mathematical performance. However, GRPO and related entropy-regularization methods still face challenges rooted in the sparse token rewards inherent to chain-of-thought (CoT). Current approaches often rely on undifferentiated token-level entropy adjustments, which frequently lead to entropy collapse or model collapse. In this work, we propose TEPO, a novel token-level framework that incorporates Markov Likelihood (sequence likelihood) links group-level rewards with tokens via token-level aggregation. Experiments show that TEPO consistently outperforms existing baselines across key metrics (including @k and accuracy). It not only sets a new state of the art on mathematical reasoning tasks but also significantly enhances training stability.

Xingyu Lin, Zhiao Huang, Yunzhu Li et al.

We consider the problem of sequential robotic manipulation of deformable objects using tools. Previous works have shown that differentiable physics simulators provide gradients to the environment state and help trajectory optimization to converge orders of magnitude faster than model-free reinforcement learning algorithms for deformable object manipulation. However, such gradient-based trajectory optimization typically requires access to the full simulator states and can only solve short-horizon, single-skill tasks due to local optima. In this work, we propose a novel framework, named DiffSkill, that uses a differentiable physics simulator for skill abstraction to solve long-horizon deformable object manipulation tasks from sensory observations. In particular, we first obtain short-horizon skills using individual tools from a gradient-based optimizer, using the full state information in a differentiable simulator; we then learn a neural skill abstractor from the demonstration trajectories which takes RGBD images as input. Finally, we plan over the skills by finding the intermediate goals and then solve long-horizon tasks. We show the advantages of our method in a new set of sequential deformable object manipulation tasks compared to previous reinforcement learning algorithms and compared to the trajectory optimizer.

Hongcheng Guo, Xingyu Lin, Jian Yang et al.

Log anomaly detection is a key component in the field of artificial intelligence for IT operations (AIOps). Considering log data of variant domains, retraining the whole network for unknown domains is inefficient in real industrial scenarios especially for low-resource domains. However, previous deep models merely focused on extracting the semantics of log sequence in the same domain, leading to poor generalization on multi-domain logs. Therefore, we propose a unified Transformer-based framework for log anomaly detection (\ourmethod{}), which is comprised of the pretraining and adapter-based tuning stage. Our model is first pretrained on the source domain to obtain shared semantic knowledge of log data. Then, we transfer the pretrained model to the target domain via the adapter-based tuning. The proposed method is evaluated on three public datasets including one source domain and two target domains. The experimental results demonstrate that our simple yet efficient approach, with fewer trainable parameters and lower training costs in the target domain, achieves state-of-the-art performance on three benchmarks.

Zizhao Hu, Ravikiran Chanumolu, Xingyu Lin et al.

Cloze task is a widely used task to evaluate an NLP system's language understanding ability. However, most of the existing cloze tasks only require NLP systems to give the relative best prediction for each input data sample, rather than the absolute quality of all possible predictions, in a consistent way across the input domain. Thus a new task is proposed: predicting if a filler word in a cloze task is a good, neutral, or bad candidate. Complicated versions can be extended to predicting more discrete classes or continuous scores. We focus on subtask A in Semeval 2022 task 7, explored some possible architectures to solve this new task, provided a detailed comparison of them, and proposed an ensemble method to improve traditional models in this new task.

Xingyu Lin, Yufei Wang, Zixuan Huang et al.

Robotic manipulation of cloth remains challenging for robotics due to the complex dynamics of the cloth, lack of a low-dimensional state representation, and self-occlusions. In contrast to previous model-based approaches that learn a pixel-based dynamics model or a compressed latent vector dynamics, we propose to learn a particle-based dynamics model from a partial point cloud observation. To overcome the challenges of partial observability, we infer which visible points are connected on the underlying cloth mesh. We then learn a dynamics model over this visible connectivity graph. Compared to previous learning-based approaches, our model poses strong inductive bias with its particle based representation for learning the underlying cloth physics; it is invariant to visual features; and the predictions can be more easily visualized. We show that our method greatly outperforms previous state-of-the-art model-based and model-free reinforcement learning methods in simulation. Furthermore, we demonstrate zero-shot sim-to-real transfer where we deploy the model trained in simulation on a Franka arm and show that the model can successfully smooth different types of cloth from crumpled configurations. Videos can be found on our project website.

Yufei Wang, Gautham Narayan Narasimhan, Xingyu Lin et al.

Current image-based reinforcement learning (RL) algorithms typically operate on the whole image without performing object-level reasoning. This leads to inefficient goal sampling and ineffective reward functions. In this paper, we improve upon previous visual self-supervised RL by incorporating object-level reasoning and occlusion reasoning. Specifically, we use unknown object segmentation to ignore distractors in the scene for better reward computation and goal generation; we further enable occlusion reasoning by employing a novel auxiliary loss and training scheme. We demonstrate that our proposed algorithm, ROLL (Reinforcement learning with Object Level Learning), learns dramatically faster and achieves better final performance compared with previous methods in several simulated visual control tasks. Project video and code are available at https://sites.google.com/andrew.cmu.edu/roll.

Xingyu Lin, Harjatin Singh Baweja, David Held

To perform robot manipulation tasks, a low-dimensional state of the environment typically needs to be estimated. However, designing a state estimator can sometimes be difficult, especially in environments with deformable objects. An alternative is to learn an end-to-end policy that maps directly from high-dimensional sensor inputs to actions. However, if this policy is trained with reinforcement learning, then without a state estimator, it is hard to specify a reward function based on high-dimensional observations. To meet this challenge, we propose a simple indicator reward function for goal-conditioned reinforcement learning: we only give a positive reward when the robot's observation exactly matches a target goal observation. We show that by relabeling the original goal with the achieved goal to obtain positive rewards (Andrychowicz et al., 2017), we can learn with the indicator reward function even in continuous state spaces. We propose two methods to further speed up convergence with indicator rewards: reward balancing and reward filtering. We show comparable performance between our method and an oracle which uses the ground-truth state for computing rewards. We show that our method can perform complex tasks in continuous state spaces such as rope manipulation from RGB-D images, without knowledge of the ground-truth state.

Xingyu Lin, Pengsheng Guo, Carlos Florensa et al.

Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of sparse-reward environments.

Hao Wang, Xingyu Lin, Yimeng Zhang et al.

Recurrent feedback connections in the mammalian visual system have been hypothesized to play a role in synthesizing input in the theoretical framework of analysis by synthesis. The comparison of internally synthesized representation with that of the input provides a validation mechanism during perceptual inference and learning. Inspired by these ideas, we proposed that the synthesis machinery can compose new, unobserved images by imagination to train the network itself so as to increase the robustness of the system in novel scenarios. As a proof of concept, we investigated whether images composed by imagination could help an object recognition system to deal with occlusion, which is challenging for the current state-of-the-art deep convolutional neural networks. We fine-tuned a network on images containing objects in various occlusion scenarios, that are imagined or self-generated through a deep generator network. Trained on imagined occluded scenarios under the object persistence constraint, our network discovered more subtle and localized image features that were neglected by the original network for object classification, obtaining better separability of different object classes in the feature space. This leads to significant improvement of object recognition under occlusion for our network relative to the original network trained only on un-occluded images. In addition to providing practical benefits in object recognition under occlusion, this work demonstrates the use of self-generated composition of visual scenes through the synthesis loop, combined with the object persistence constraint, can provide opportunities for neural networks to discover new relevant patterns in the data, and become more flexible in dealing with novel situations.

Xingyu Lin, Hao Wang, Zhihao Li et al.

We develop a model of perceptual similarity judgment based on re-training a deep convolution neural network (DCNN) that learns to associate different views of each 3D object to capture the notion of object persistence and continuity in our visual experience. The re-training process effectively performs distance metric learning under the object persistency constraints, to modify the view-manifold of object representations. It reduces the effective distance between the representations of different views of the same object without compromising the distance between those of the views of different objects, resulting in the untangling of the view-manifolds between individual objects within the same category and across categories. This untangling enables the model to discriminate and recognize objects within the same category, independent of viewpoints. We found that this ability is not limited to the trained objects, but transfers to novel objects in both trained and untrained categories, as well as to a variety of completely novel artificial synthetic objects. This transfer in learning suggests the modification of distance metrics in view- manifolds is more general and abstract, likely at the levels of parts, and independent of the specific objects or categories experienced during training. Interestingly, the resulting transformation of feature representation in the deep networks is found to significantly better match human perceptual similarity judgment than AlexNet, suggesting that object persistence could be an important constraint in the development of perceptual similarity judgment in biological neural networks.