Andrew Choi

Andrew Choi, Mohammad Khalid Jawed, Jungseock Joo

As technology advances, the need for safe, efficient, and collaborative human-robot-teams has become increasingly important. One of the most fundamental collaborative tasks in any setting is the object handover. Human-to-robot handovers can take either of two approaches: (1) direct hand-to-hand or (2) indirect hand-to-placement-to-pick-up. The latter approach ensures minimal contact between the human and robot but can also result in increased idle time due to having to wait for the object to first be placed down on a surface. To minimize such idle time, the robot must preemptively predict the human intent of where the object will be placed. Furthermore, for the robot to preemptively act in any sort of productive manner, predictions and motion planning must occur in real-time. We introduce a novel prediction-planning pipeline that allows the robot to preemptively move towards the human agent's intended placement location using gaze and gestures as model inputs. In this paper, we investigate the performance and drawbacks of our early intent predictor-planner as well as the practical benefits of using such a pipeline through a human-robot case study.

Arvind Murari Vepa, Zukang Yang, Andrew Choi et al.

Deep learning has seen remarkable advancements in machine learning, yet it often demands extensive annotated data. Tasks like 3D semantic segmentation impose a substantial annotation burden, especially in domains like medicine, where expert annotations drive up the cost. Active learning (AL) holds great potential to alleviate this annotation burden in 3D medical segmentation. The majority of existing AL methods, however, are not tailored to the medical domain. While weakly-supervised methods have been explored to reduce annotation burden, the fusion of AL with weak supervision remains unexplored, despite its potential to significantly reduce annotation costs. Additionally, there is little focus on slice-based AL for 3D segmentation, which can also significantly reduce costs in comparison to conventional volume-based AL. This paper introduces a novel metric learning method for Coreset to perform slice-based active learning in 3D medical segmentation. By merging contrastive learning with inherent data groupings in medical imaging, we learn a metric that emphasizes the relevant differences in samples for training 3D medical segmentation models. We perform comprehensive evaluations using both weak and full annotations across four datasets (medical and non-medical). Our findings demonstrate that our approach surpasses existing active learning techniques on both weak and full annotations and obtains superior performance with low-annotation budgets which is crucial in medical imaging. Source code for this project is available in the supplementary materials and on GitHub: https://github.com/arvindmvepa/al-seg.

Andrew Choi, Dezhong Tong

With the explosive growth of rigid-body simulators, policy learning in simulation has become the de facto standard for most rigid morphologies. In contrast, soft robotic simulation frameworks remain scarce and are seldom adopted by the soft robotics community. This gap stems partly from the lack of easy-to-use, general-purpose frameworks and partly from the high computational cost of accurately simulating continuum mechanics, which often renders policy learning infeasible. In this work, we demonstrate that rapid soft robot policy learning is indeed achievable via implicit time-stepping. Our simulator of choice, DisMech, is a general-purpose, fully implicit soft-body simulator capable of handling both soft dynamics and frictional contact. We further introduce delta natural curvature control, a method analogous to delta joint position control in rigid manipulators, providing an intuitive and effective means of enacting control for soft robot learning. To highlight the benefits of implicit time-stepping and delta curvature control, we conduct extensive comparisons across four diverse soft manipulator tasks against one of the most widely used soft-body frameworks, Elastica. With implicit time-stepping, parallel stepping of 500 environments achieves up to 6x faster speeds for non-contact cases and up to 40x faster for contact-rich scenarios. Finally, a comprehensive sim-to-sim gap evaluation--training policies in one simulator and evaluating them in another--demonstrates that implicit time-stepping provides a rare free lunch: dramatic speedups achieved without sacrificing accuracy.

Andrew Choi, Xinjie Wang, Zhizhong Su et al.

The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fine-tuning vision-language-action (VLA) models in robotics. Many recent works fine-tune VLAs directly in the real world to avoid addressing the sim-to-real gap. While real-world RL circumvents sim-to-real issues, it inherently limits the generality of the resulting VLA, as scaling scene and object diversity in the physical world is prohibitively difficult. This leads to the paradoxical outcome of transforming a broadly pretrained model into an overfitted, scene-specific policy. Training in simulation can instead provide access to diverse scenes, but designing those scenes is also costly. In this work, we show that VLAs can be RL fine-tuned without sacrificing generality and with reduced labor by leveraging 3D world generative models. Using these models together with a language-driven scene designer, we generate hundreds of diverse interactive scenes containing unique objects and backgrounds, enabling scalable and highly parallel policy learning. Starting from a pretrained imitation baseline, our approach increases simulation success from 9.7% to 79.8% while achieving a 1.25$\times$ speedup in task completion time. We further demonstrate successful sim-to-real transfer enabled by the quality of the generated digital twins together with domain randomization, improving real-world success from 21.7% to 75% and achieving a 1.13$\times$ speedup. Finally, we further highlight the benefits of leveraging the effectively unlimited data from 3D world generative models through an ablation study showing that increasing scene diversity directly improves zero-shot generalization.

Andrew Choi, Wei Xu

Offline-to-online reinforcement learning (RL) improves sample efficiency by leveraging pre-collected datasets prior to online interaction. A key challenge, however, is learning an accurate critic in large state--action spaces with limited dataset coverage. To mitigate harmful updates from value overestimation, prior methods impose pessimism by down-weighting out-of-distribution (OOD) actions relative to dataset actions. While effective, this essentially acts as a behavior cloning anchor and can hinder downstream online policy improvement when dataset actions are suboptimal. We propose RankQ, an offline-to-online Q-learning objective that augments temporal-difference learning with a self-supervised multi-term ranking loss to enforce structured action ordering. By learning relative action preferences rather than uniformly penalizing unseen actions, RankQ shapes the Q-function such that action gradients are directed toward higher-quality behaviors. Across sparse reward D4RL benchmarks, RankQ achieves performance competitive with or superior to seven prior methods. In vision-based robot learning, RankQ enables effective offline-to-online fine-tuning of a pretrained vision-language-action (VLA) model in a low-data regime, achieving on average a 42.7% higher simulation success rate than the next best method. In a high-data setting, RankQ improves simulation performance by 13.7% over the next best method and achieves strong sim-to-real transfer, increasing real-world cube stacking success from 43.1% to 84.7% relative to the VLA's initial performance.

Haichao Zhang, Haonan Yu, Le Zhao et al.

We present a low-cost legged mobile manipulation system that solves long-horizon real-world tasks, trained by reinforcement learning purely in simulation. This system is made possible by 1) a hierarchical design of a high-level policy for visual-mobile manipulation following task instructions, and a low-level quadruped locomotion policy, 2) a teacher and student training pipeline for the high level, which trains a teacher to tackle long-horizon tasks using privileged task decomposition and target object information, and further trains a student for visual-mobile manipulation via RL guided by the teacher's behavior, and 3) a suite of techniques for minimizing the sim-to-real gap. In contrast to many previous works that use high-end equipments, our system demonstrates effective performance with more accessible hardware -- specifically, a Unitree Go1 quadruped, a WidowX-250S arm, and a single wrist-mounted RGB camera -- despite the increased challenges of sim-to-real transfer. Trained fully in simulation, a single policy autonomously solves long-horizon tasks involving search, move to, grasp, transport, and drop into, achieving nearly 80% real-world success. This performance is comparable to that of expert human teleoperation on the same tasks while the robot is more efficient, operating at about 1.5x the speed of the teleoperation. Finally, we perform extensive ablations on key techniques for efficient RL training and effective sim-to-real transfer, and demonstrate effective deployment across diverse indoor and outdoor scenes under various lighting conditions.

Mengdan Zhu, Raasikh Kanjiani, Jiahui Lu et al.

Deep generative models like VAEs and diffusion models have advanced various generation tasks by leveraging latent variables to learn data distributions and generate high-quality samples. Despite the field of explainable AI making strides in interpreting machine learning models, understanding latent variables in generative models remains challenging. This paper introduces LatentExplainer, a framework for automatically generating semantically meaningful explanations of latent variables in deep generative models. LatentExplainer tackles three main challenges: inferring the meaning of latent variables, aligning explanations with inductive biases, and handling varying degrees of explainability. Our approach perturbs latent variables, interprets changes in generated data, and uses multimodal large language models (MLLMs) to produce human-understandable explanations. We evaluate our proposed method on several real-world and synthetic datasets, and the results demonstrate superior performance in generating high-quality explanations for latent variables. The results highlight the effectiveness of incorporating inductive biases and uncertainty quantification, significantly enhancing model interpretability.