arXiv subjects

Changhyun Choi

Publications and source records attributed to Changhyun Choi.

At least 19 recordsLinked to original sources

arXiv2026

Self-Supervised Pretraining Improves Cross-Site and Cross-Scale Robustness of Point Cloud Leaf-Wood Segmentation

The accuracy of existing leaf-wood segmentation methods for tree point clouds varies across forest types and sites. Self-supervised learning (SSL) on point clouds has improved the generalization of deep learning models for forestry point cloud tasks, including biomass regression and individual tree segmentation, but its applicability to leaf-wood segmentation remains untested. In this study, we pretrained Point-M2AE, a widely used SSL architecture for point clouds, on ShapeNet-55 augmented with 2,400 individual tree point clouds. For fine-tuning and inference, we used recursive voxel subdivision to handle the wide variation in point density across inputs, allowing the same model to operate at both individual-tree and plot scales without architecture change. Compared to the model without pretraining, the pretrained model improved wood IoU from 60.5% to 70.0% for needleleaf and from 69.7% to 76.3% for broadleaf trees. On a benchmark spanning four countries across three climatic zones, the pretrained model achieved the smallest cross-site variation and highest overall performance among compared methods (LeWos, CWLS, and PointTransformer). Plot-level segmentation maintained accuracy comparable to individual-tree performance, with mIoU of 84.7% for broadleaf and 77.7% for needleleaf plots, showing that the model generalizes across scales without additional finetuning. As a downstream test in tropical forests, where dense canopies make segmentation challenging, we applied our model and a quantitative structure model to estimate wood volume for 28 trees from Guyana, Indonesia, and Peru to assess whether the segmentation improvements from SSL pretraining translate into improved downstream performance. The resulting volume estimates achieved the lowest error among all methods tested (MAE = 2.40 m$^3$), less than half that of algorithmic baselines (LeWos: 5.94 m$^3$; CWLS: 5.27 m$^3$).

cs.CV↗

arXiv2026

LAMP: Lane-Aligned Motion Primitives for Feasible Trajectory Prediction

Motion forecasting is essential for autonomous driving systems to enable safe decision-making and planning in complex driving scenarios. While existing predictors excel at minimizing standard displacement errors, they often overlook the adherence to lane topology of multimodal predictions, particularly for lower-probability modes. Consequently, predicted trajectories may violate physical and logical constraints, making the prediction set unreliable for safety-critical planning. In this paper, we propose LAMP (Lane-Aligned Motion Primitives), a topology-aware forecasting framework that anchors multimodal prediction to structured motion primitives aligned with lane topology. Specifically, we use a VQ-VAE to learn shape-aware motion primitives as discrete intention queries, capturing spatiotemporal patterns beyond endpoint-based intentions. We further introduce a feasibility-aware intention selector trained with a lane-topology prior for filtering unreachable intention queries, guiding the decoder to prioritize topology-consistent intentions while preserving behavioral diversity. Extensive experiments on the Argoverse 2 dataset demonstrate that LAMP achieves prediction accuracy comparable to state-of-the-art baselines while outperforming them in feasibility and diversity metrics.

cs.RO↗

arXiv2026

LACY: A Vision-Language Model-based Language-Action Cycle for Self-Improving Robotic Manipulation

Learning generalizable policies for robotic manipulation increasingly relies on large-scale models that map language instructions to actions (L2A). However, this one-way paradigm often produces policies that execute tasks without deeper contextual understanding, limiting their ability to generalize or explain their behavior. We argue that the complementary skill of mapping actions back to language (A2L) is essential for developing more holistic grounding. An agent capable of both acting and explaining its actions can form richer internal representations and unlock new paradigms for self-supervised learning. We introduce LACY (Language-Action Cycle), a unified framework that learns such bidirectional mappings within a single vision-language model. LACY is jointly trained on three synergistic tasks: generating parameterized actions from language (L2A), explaining observed actions in language (A2L), and verifying semantic consistency between two language descriptions (L2C). This enables a self-improving cycle that autonomously generates and filters new training data through an active augmentation strategy targeting low-confidence cases, thereby improving the model without additional human labels. Experiments on pick-and-place tasks in both simulation and the real world show that LACY improves task success rates by 56.46% on average and yields more robust language-action grounding for robotic manipulation. Project page: https://vla2026.github.io/LACY/

cs.RO↗

arXiv2026

Hierarchical DLO Routing with Reinforcement Learning and In-Context Vision-language Models

Long-horizon routing tasks of deformable linear objects (DLOs), such as cables and ropes, are common in industrial assembly lines and everyday life. These tasks are particularly challenging because they require robots to manipulate DLO with long-horizon planning and reliable skill execution. Successfully completing such tasks demands adapting to their nonlinear dynamics, decomposing abstract routing goals, and generating multi-step plans composed of multiple skills, all of which require accurate high-level reasoning during execution. In this paper, we propose a fully autonomous hierarchical framework for solving challenging DLO routing tasks. Given an implicit or explicit routing goal expressed in language, our framework leverages vision-language models~(VLMs) for in-context high-level reasoning to synthesize feasible plans, which are then executed by low-level skills trained via reinforcement learning. To improve robustness over long horizons, we further introduce a failure recovery mechanism that reorients the DLO into insertion-feasible states. Our approach generalizes to diverse scenes involving object attributes, spatial descriptions, implicit language commands, and \myred{extended 5-clip settings}. It achieves an overall success rate of 92\% across long-horizon routing scenarios. Please refer to our project page: https://icra2026-dloroute.github.io/DLORoute/

cs.RO↗

arXiv2026

Temporal Action Representation Learning for Tactical Resource Control and Subsequent Maneuver Generation

Autonomous robotic systems should reason about resource control and its impact on subsequent maneuvers, especially when operating with limited energy budgets or restricted sensing. Learning-based control is effective in handling complex dynamics and represents the problem as a hybrid action space unifying discrete resource usage and continuous maneuvers. However, prior works on hybrid action space have not sufficiently captured the causal dependencies between resource usage and maneuvers. They have also overlooked the multi-modal nature of tactical decisions, both of which are critical in fast-evolving scenarios. In this paper, we propose TART, a Temporal Action Representation learning framework for Tactical resource control and subsequent maneuver generation. TART leverages contrastive learning based on a mutual information objective, designed to capture inherent temporal dependencies in resource-maneuver interactions. These learned representations are quantized into discrete codebook entries that condition the policy, capturing recurring tactical patterns and enabling multi-modal and temporally coherent behaviors. We evaluate TART in two domains where resource deployment is critical: (i) a maze navigation task where a limited budget of discrete actions provides enhanced mobility, and (ii) a high-fidelity air combat simulator in which an F-16 agent operates weapons and defensive systems in coordination with flight maneuvers. Across both domains, TART consistently outperforms hybrid-action baselines, demonstrating its effectiveness in leveraging limited resources and producing context-aware subsequent maneuvers.

cs.RO↗

arXiv2025

Attribute-based Object Grounding and Robot Grasp Detection with Spatial Reasoning

Enabling robots to grasp objects specified through natural language is essential for effective human-robot interaction, yet it remains a significant challenge. Existing approaches often struggle with open-form language expressions and typically assume unambiguous target objects without duplicates. Moreover, they frequently rely on costly, dense pixel-wise annotations for both object grounding and grasp configuration. We present Attribute-based Object Grounding and Robotic Grasping (OGRG), a novel framework that interprets open-form language expressions and performs spatial reasoning to ground target objects and predict planar grasp poses, even in scenes containing duplicated object instances. We investigate OGRG in two settings: (1) Referring Grasp Synthesis (RGS) under pixel-wise full supervision, and (2) Referring Grasp Affordance (RGA) using weakly supervised learning with only single-pixel grasp annotations. Key contributions include a bi-directional vision-language fusion module and the integration of depth information to enhance geometric reasoning, improving both grounding and grasping performance. Experiment results show that OGRG outperforms strong baselines in tabletop scenes with diverse spatial language instructions. In RGS, it operates at 17.59 FPS on a single NVIDIA RTX 2080 Ti GPU, enabling potential use in closed-loop or multi-object sequential grasping, while delivering superior grounding and grasp prediction accuracy compared to all the baselines considered. Under the weakly supervised RGA setting, OGRG also surpasses baseline grasp-success rates in both simulation and real-robot trials, underscoring the effectiveness of its spatial reasoning design. Project page: https://z.umn.edu/ogrg

cs.RO↗

arXiv2025

Performance Plateaus in Inference-Time Scaling for Text-to-Image Diffusion Without External Models

Recently, it has been shown that investing computing resources in searching for good initial noise for a text-to-image diffusion model helps improve performance. However, previous studies required external models to evaluate the resulting images, which is impossible on GPUs with small VRAM. For these reasons, we apply Best-of-N inference-time scaling to algorithms that optimize the initial noise of a diffusion model without external models across multiple datasets and backbones. We demonstrate that inference-time scaling for text-to-image diffusion models in this setting quickly reaches a performance plateau, and a relatively small number of optimization steps suffices to achieve the maximum achievable performance with each algorithm.

cs.CV↗

arXiv2025

Optimal Robotic Velcro Peeling with Force Feedback

We study the problem of peeling a Velcro strap from a surface using a robotic manipulator. The surface geometry is arbitrary and unknown. The robot has access to only the force feedback and its end-effector position. This problem is challenging due to the partial observability of the environment and the incompleteness of the sensor feedback. To solve it, we first model the system with simple analytic state and action models based on quasi-static dynamics assumptions. We then study the fully-observable case where the state of both the Velcro and the robot are given. For this case, we obtain the optimal solution in closed-form which minimizes the total energy cost. Next, for the partially-observable case, we design a state estimator which estimates the underlying state using only force and position feedback. Then, we present a heuristics-based controller that balances exploratory and exploitative behaviors in order to peel the velcro efficiently. Finally, we evaluate our proposed method in environments with complex geometric uncertainties and sensor noises, achieving 100% success rate with less than 80% increase in energy cost compared to the optimal solution when the environment is fully-observable, outperforming the baselines by a large margin.

cs.RO↗

arXiv2025

A Parameter-Efficient Tuning Framework for Language-guided Object Grounding and Robot Grasping

The language-guided robot grasping task requires a robot agent to integrate multimodal information from both visual and linguistic inputs to predict actions for target-driven grasping. While recent approaches utilizing Multimodal Large Language Models (MLLMs) have shown promising results, their extensive computation and data demands limit the feasibility of local deployment and customization. To address this, we propose a novel CLIP-based multimodal parameter-efficient tuning (PET) framework designed for three language-guided object grounding and grasping tasks: (1) Referring Expression Segmentation (RES), (2) Referring Grasp Synthesis (RGS), and (3) Referring Grasp Affordance (RGA). Our approach introduces two key innovations: a bi-directional vision-language adapter that aligns multimodal inputs for pixel-level language understanding and a depth fusion branch that incorporates geometric cues to facilitate robot grasping predictions. Experiment results demonstrate superior performance in the RES object grounding task compared with existing CLIP-based full-model tuning or PET approaches. In the RGS and RGA tasks, our model not only effectively interprets object attributes based on simple language descriptions but also shows strong potential for comprehending complex spatial reasoning scenarios, such as multiple identical objects present in the workspace. Project page: https://z.umn.edu/etog-etrg

cs.RO↗

arXiv2025

Attribute-Based Robotic Grasping with Data-Efficient Adaptation

Robotic grasping is one of the most fundamental robotic manipulation tasks and has been the subject of extensive research. However, swiftly teaching a robot to grasp a novel target object in clutter remains challenging. This paper attempts to address the challenge by leveraging object attributes that facilitate recognition, grasping, and rapid adaptation to new domains. In this work, we present an end-to-end encoder-decoder network to learn attribute-based robotic grasping with data-efficient adaptation capability. We first pre-train the end-to-end model with a variety of basic objects to learn generic attribute representation for recognition and grasping. Our approach fuses the embeddings of a workspace image and a query text using a gated-attention mechanism and learns to predict instance grasping affordances. To train the joint embedding space of visual and textual attributes, the robot utilizes object persistence before and after grasping. Our model is self-supervised in a simulation that only uses basic objects of various colors and shapes but generalizes to novel objects in new environments. To further facilitate generalization, we propose two adaptation methods, adversarial adaption and one-grasp adaptation. Adversarial adaptation regulates the image encoder using augmented data of unlabeled images, whereas one-grasp adaptation updates the overall end-to-end model using augmented data from one grasp trial. Both adaptation methods are data-efficient and considerably improve instance grasping performance. Experimental results in both simulation and the real world demonstrate that our approach achieves over 81% instance grasping success rate on unknown objects, which outperforms several baselines by large margins.

cs.RO↗

arXiv2024

Learning for Deformable Linear Object Insertion Leveraging Flexibility Estimation from Visual Cues

Manipulation of deformable Linear objects (DLOs), including iron wire, rubber, silk, and nylon rope, is ubiquitous in daily life. These objects exhibit diverse physical properties, such as Young$'$s modulus and bending stiffness.Such diversity poses challenges for developing generalized manipulation policies. However, previous research limited their scope to single-material DLOs and engaged in time-consuming data collection for the state estimation. In this paper, we propose a two-stage manipulation approach consisting of a material property (e.g., flexibility) estimation and policy learning for DLO insertion with reinforcement learning. Firstly, we design a flexibility estimation scheme that characterizes the properties of different types of DLOs. The ground truth flexibility data is collected in simulation to train our flexibility estimation module. During the manipulation, the robot interacts with the DLOs to estimate flexibility by analyzing their visual configurations. Secondly, we train a policy conditioned on the estimated flexibility to perform challenging DLO insertion tasks. Our pipeline trained with diverse insertion scenarios achieves an 85.6% success rate in simulation and 66.67% in real robot experiments. Please refer to our project page: https://lmeee.github.io/DLOInsert/

cs.RO↗

arXiv2023

SlotGNN: Unsupervised Discovery of Multi-Object Representations and Visual Dynamics

Learning multi-object dynamics from visual data using unsupervised techniques is challenging due to the need for robust, object representations that can be learned through robot interactions. This paper presents a novel framework with two new architectures: SlotTransport for discovering object representations from RGB images and SlotGNN for predicting their collective dynamics from RGB images and robot interactions. Our SlotTransport architecture is based on slot attention for unsupervised object discovery and uses a feature transport mechanism to maintain temporal alignment in object-centric representations. This enables the discovery of slots that consistently reflect the composition of multi-object scenes. These slots robustly bind to distinct objects, even under heavy occlusion or absence. Our SlotGNN, a novel unsupervised graph-based dynamics model, predicts the future state of multi-object scenes. SlotGNN learns a graph representation of the scene using the discovered slots from SlotTransport and performs relational and spatial reasoning to predict the future appearance of each slot conditioned on robot actions. We demonstrate the effectiveness of SlotTransport in learning object-centric features that accurately encode both visual and positional information. Further, we highlight the accuracy of SlotGNN in downstream robotic tasks, including challenging multi-object rearrangement and long-horizon prediction. Finally, our unsupervised approach proves effective in the real world. With only minimal additional data, our framework robustly predicts slots and their corresponding dynamics in real-world control tasks.

cs.RO↗

arXiv2023

Adversarial Object Rearrangement in Constrained Environments with Heterogeneous Graph Neural Networks

Adversarial object rearrangement in the real world (e.g., previously unseen or oversized items in kitchens and stores) could benefit from understanding task scenes, which inherently entail heterogeneous components such as current objects, goal objects, and environmental constraints. The semantic relationships among these components are distinct from each other and crucial for multi-skilled robots to perform efficiently in everyday scenarios. We propose a hierarchical robotic manipulation system that learns the underlying relationships and maximizes the collaborative power of its diverse skills (e.g., pick-place, push) for rearranging adversarial objects in constrained environments. The high-level coordinator employs a heterogeneous graph neural network (HetGNN), which reasons about the current objects, goal objects, and environmental constraints; the low-level 3D Convolutional Neural Network-based actors execute the action primitives. Our approach is trained entirely in simulation, and achieved an average success rate of 87.88% and a planning cost of 12.82 in real-world experiments, surpassing all baseline methods. Supplementary material is available at https://sites.google.com/umn.edu/versatile-rearrangement.

cs.RO↗

arXiv2023

IOSG: Image-driven Object Searching and Grasping

When robots retrieve specific objects from cluttered scenes, such as home and warehouse environments, the target objects are often partially occluded or completely hidden. Robots are thus required to search, identify a target object, and successfully grasp it. Preceding works have relied on pre-trained object recognition or segmentation models to find the target object. However, such methods require laborious manual annotations to train the models and even fail to find novel target objects. In this paper, we propose an Image-driven Object Searching and Grasping (IOSG) approach where a robot is provided with the reference image of a novel target object and tasked to find and retrieve it. We design a Target Similarity Network that generates a probability map to infer the location of the novel target. IOSG learns a hierarchical policy; the high-level policy predicts the subtask type, whereas the low-level policies, explorer and coordinator, generate effective push and grasp actions. The explorer is responsible for searching the target object when it is hidden or occluded by other objects. Once the target object is found, the coordinator conducts target-oriented pushing and grasping to retrieve the target from the clutter. The proposed pipeline is trained with full self-supervision in simulation and applied to a real environment. Our model achieves a 96.0% and 94.5% task success rate on coordination and exploration tasks in simulation respectively, and 85.0% success rate on a real robot for the search-and-grasp task.

cs.RO↗

arXiv2023

KINet: Unsupervised Forward Models for Robotic Pushing Manipulation

Object-centric representation is an essential abstraction for forward prediction. Most existing forward models learn this representation through extensive supervision (e.g., object class and bounding box) although such ground-truth information is not readily accessible in reality. To address this, we introduce KINet (Keypoint Interaction Network) -- an end-to-end unsupervised framework to reason about object interactions based on a keypoint representation. Using visual observations, our model learns to associate objects with keypoint coordinates and discovers a graph representation of the system as a set of keypoint embeddings and their relations. It then learns an action-conditioned forward model using contrastive estimation to predict future keypoint states. By learning to perform physical reasoning in the keypoint space, our model automatically generalizes to scenarios with a different number of objects, novel backgrounds, and unseen object geometries. Experiments demonstrate the effectiveness of our model in accurately performing forward prediction and learning plannable object-centric representations for downstream robotic pushing manipulation tasks.

cs.CV↗

arXiv2023

Active Mass Distribution Estimation from Tactile Feedback

In this work, we present a method to estimate the mass distribution of a rigid object through robotic interactions and tactile feedback. This is a challenging problem because of the complexity of physical dynamics modeling and the action dependencies across the model parameters. We propose a sequential estimation strategy combined with a set of robot action selection rules based on the analytical formulation of a discrete-time dynamics model. To evaluate the performance of our approach, we also manufactured re-configurable block objects that allow us to modify the object mass distribution while having access to the ground truth values. We compare our approach against multiple baselines and show that our approach can estimate the mass distribution with around 10% error, while the baselines have errors ranging from 18% to 68%.

cs.RO↗

arXiv2022

Self-Supervised Interactive Object Segmentation Through a Singulation-and-Grasping Approach

Instance segmentation with unseen objects is a challenging problem in unstructured environments. To solve this problem, we propose a robot learning approach to actively interact with novel objects and collect each object's training label for further fine-tuning to improve the segmentation model performance, while avoiding the time-consuming process of manually labeling a dataset. The Singulation-and-Grasping (SaG) policy is trained through end-to-end reinforcement learning. Given a cluttered pile of objects, our approach chooses pushing and grasping motions to break the clutter and conducts object-agnostic grasping for which the SaG policy takes as input the visual observations and imperfect segmentation. We decompose the problem into three subtasks: (1) the object singulation subtask aims to separate the objects from each other, which creates more space that alleviates the difficulty of (2) the collision-free grasping subtask; (3) the mask generation subtask to obtain the self-labeled ground truth masks by using an optical flow-based binary classifier and motion cue post-processing for transfer learning. Our system achieves 70% singulation success rate in simulated cluttered scenes. The interactive segmentation of our system achieves 87.8%, 73.9%, and 69.3% average precision for toy blocks, YCB objects in simulation and real-world novel objects, respectively, which outperforms several baselines.

cs.RO↗

arXiv2022

Interactive Robotic Grasping with Attribute-Guided Disambiguation

Interactive robotic grasping using natural language is one of the most fundamental tasks in human-robot interaction. However, language can be a source of ambiguity, particularly when there are ambiguous visual or linguistic contents. This paper investigates the use of object attributes in disambiguation and develops an interactive grasping system capable of effectively resolving ambiguities via dialogues. Our approach first predicts target scores and attribute scores through vision-and-language grounding. To handle ambiguous objects and commands, we propose an attribute-guided formulation of the partially observable Markov decision process (Attr-POMDP) for disambiguation. The Attr-POMDP utilizes target and attribute scores as the observation model to calculate the expected return of an attribute-based (e.g., "what is the color of the target, red or green?") or a pointing-based (e.g., "do you mean this one?") question. Our disambiguation module runs in real time on a real robot, and the interactive grasping system achieves a 91.43\% selection accuracy in the real-robot experiments, outperforming several baselines by large margins.

cs.RO↗