Jongeun Choi

Hyunwoo Ryu, Hong-in Lee, Jeong-Hoon Lee et al.

End-to-end learning for visual robotic manipulation is known to suffer from sample inefficiency, requiring large numbers of demonstrations. The spatial roto-translation equivariance, or the SE(3)-equivariance can be exploited to improve the sample efficiency for learning robotic manipulation. In this paper, we present SE(3)-equivariant models for visual robotic manipulation from point clouds that can be trained fully end-to-end. By utilizing the representation theory of the Lie group, we construct novel SE(3)-equivariant energy-based models that allow highly sample efficient end-to-end learning. We show that our models can learn from scratch without prior knowledge and yet are highly sample efficient (5~10 demonstrations are enough). Furthermore, we show that our models can generalize to tasks with (i) previously unseen target object poses, (ii) previously unseen target object instances of the category, and (iii) previously unseen visual distractors. We experiment with 6-DoF robotic manipulation tasks to validate our models' sample efficiency and generalizability. Codes are available at: https://github.com/tomato1mule/edf

Hyunwoo Ryu, Jiwoo Kim, Hyunseok An et al.

Diffusion generative modeling has become a promising approach for learning robotic manipulation tasks from stochastic human demonstrations. In this paper, we present Diffusion-EDFs, a novel SE(3)-equivariant diffusion-based approach for visual robotic manipulation tasks. We show that our proposed method achieves remarkable data efficiency, requiring only 5 to 10 human demonstrations for effective end-to-end training in less than an hour. Furthermore, our benchmark experiments demonstrate that our approach has superior generalizability and robustness compared to state-of-the-art methods. Lastly, we validate our methods with real hardware experiments. Project Website: https://sites.google.com/view/diffusion-edfs/home

Junwoo Chang, Hyunwoo Ryu, Jiwoo Kim et al.

Diffusion models have risen as a powerful tool in robotics due to their flexibility and multi-modality. While some of these methods effectively address complex problems, they often depend heavily on inference-time obstacle detection and require additional equipment. Addressing these challenges, we present a method that, during inference time, simultaneously generates only reachable goals and plans motions that avoid obstacles, all from a single visual input. Central to our approach is the novel use of a collision-avoiding diffusion kernel for training. Through evaluations against behavior-cloning and classical diffusion models, our framework has proven its robustness. It is particularly effective in multi-modal environments, navigating toward goals and avoiding unreachable ones blocked by obstacles, while ensuring collision avoidance. Project Website: https://sites.google.com/view/denoising-heat-inspired

Nikhil Potu Surya Prakash, Joohwan Seo, Jongeun Choi et al.

In Robust Control and Data Driven Robust Control design methodologies, multiple plant transfer functions or a family of transfer functions are considered and a common controller is designed such that all the plants that fall into this family are stabilized. Though the plants are stabilized, the controller might be sub-optimal for each of the plants when the variations in the plants are large. This paper presents a way of clustering stable linear dynamical systems for the design of robust controllers within each of the clusters such that the controllers are optimal for each of the clusters. First a k-medoids algorithm for hard clustering will be presented for stable Linear Time Invariant (LTI) systems and then a Gaussian Mixture Models (GMM) clustering for a special class of LTI systems, common for Hard Disk Drive plants, will be presented.

Junwoo Chang, Minwoo Park, Joohwan Seo et al.

Group symmetries provide a powerful inductive bias for reinforcement learning (RL), enabling efficient generalization across symmetric states and actions via group-invariant Markov Decision Processes (MDPs). However, real-world environments almost never realize fully group-invariant MDPs; dynamics, actuation limits, and reward design usually break symmetries, often only locally. Under group-invariant Bellman backups for such cases, local symmetry-breaking introduces errors that propagate across the entire state-action space, resulting in global value estimation errors. To address this, we introduce Partially group-Invariant MDP (PI-MDP), which selectively applies group-invariant or standard Bellman backups depending on where symmetry holds. This framework mitigates error propagation from locally broken symmetries while maintaining the benefits of equivariance, thereby enhancing sample efficiency and generalizability. Building on this framework, we present practical RL algorithms -- Partially Equivariant (PE)-DQN for discrete control and PE-SAC for continuous control -- that combine the benefits of equivariance with robustness to symmetry-breaking. Experiments across Grid-World, locomotion, and manipulation benchmarks demonstrate that PE-DQN and PE-SAC significantly outperform baselines, highlighting the importance of selective symmetry exploitation for robust and sample-efficient RL.

Junwoo Chang, Joseph Park, Roberto Horowitz et al.

Unsupervised skill discovery aims to acquire behavior primitives that improve exploration and accelerate downstream task learning. However, existing approaches often ignore the geometric symmetries of physical environments, leading to redundant behaviors and sample inefficiency. To address this, we introduce Group-Invariant Skill Discovery (GISD), a framework that explicitly embeds group structure into the skill discovery objective. Our approach is grounded in a theoretical guarantee: we prove that in group-symmetric environments, the standard Wasserstein dependency measure admits a globally optimal solution comprised of an equivariant policy and a group-invariant scoring function. Motivated by this, we formulate the Group-Invariant Wasserstein dependency measure, which restricts the optimization to this symmetry-aware subspace without loss of optimality. Practically, we parameterize the scoring function using a group Fourier representation and define the intrinsic reward via the alignment of equivariant latent features, ensuring that the discovered skills generalize systematically under group transformations. Experiments on state-based and pixel-based locomotion benchmarks demonstrate that GISD achieves broader state-space coverage and improved efficiency in downstream task learning compared to a strong baseline.

Minwoo Park, Junwoo Chang, Jongeun Choi et al.

Equivariant diffusion policies (EDPs) combine the generative expressivity of diffusion models with the strong generalization and sample efficiency afforded by geometric symmetries. While steering these policies with reinforcement learning (RL) offers a promising mechanism for fine-tuning beyond demonstration data, directly applying standard (non-equivariant) RL can be sample-inefficient and unstable, as it ignores the symmetries that EDPs are designed to exploit. In this paper, we theoretically establish that the diffusion process of an EDP is equivariant, which in turn induces a group-invariant latent-noise MDP that is well-suited for equivariant diffusion steering. Building on this theory, we introduce a principled symmetry-aware steering framework and compare standard, equivariant, and approximately equivariant RL strategies through comprehensive experiments across tasks with varying degrees of symmetry. While we identify the practical boundaries of strict equivariance under symmetry breaking, we show that exploiting symmetry during the steering process yields substantial benefits-enhancing sample efficiency, preventing value divergence, and achieving strong policy improvements even when EDPs are trained from extremely limited demonstrations.

Joohwan Seo, Soochul Yoo, Junwoo Chang et al.

Recent advances in deep learning and Transformers have driven major breakthroughs in robotics by employing techniques such as imitation learning, reinforcement learning, and LLM-based multimodal perception and decision-making. However, conventional deep learning and Transformer models often struggle to process data with inherent symmetries and invariances, typically relying on large datasets or extensive data augmentation. Equivariant neural networks overcome these limitations by explicitly integrating symmetry and invariance into their architectures, leading to improved efficiency and generalization. This tutorial survey reviews a wide range of equivariant deep learning and control methods for robotics, from classic to state-of-the-art, with a focus on SE(3)-equivariant models that leverage the natural 3D rotational and translational symmetries in visual robotic manipulation and control design. Using unified mathematical notation, we begin by reviewing key concepts from group theory, along with matrix Lie groups and Lie algebras. We then introduce foundational group-equivariant neural network design and show how the group-equivariance can be obtained through their structure. Next, we discuss the applications of SE(3)-equivariant neural networks in robotics in terms of imitation learning and reinforcement learning. The SE(3)-equivariant control design is also reviewed from the perspective of geometric control. Finally, we highlight the challenges and future directions of equivariant methods in developing more robust, sample-efficient, and multi-modal real-world robotic systems.

Sarmad Idrees, Jongeun Choi, Seokman Sohn

To achieve seamless collaboration between robots and humans in a shared environment, accurately predicting future human movements is essential. Human motion prediction has traditionally been approached as a sequence prediction problem, leveraging historical human motion data to estimate future poses. Beginning with vanilla recurrent networks, the research community has investigated a variety of methods for learning human motion dynamics, encompassing graph-based and generative approaches. Despite these efforts, achieving accurate long-term predictions continues to be a significant challenge. In this regard, we present the Adversarial Motion Transformer (AdvMT), a novel model that integrates a transformer-based motion encoder and a temporal continuity discriminator. This combination effectively captures spatial and temporal dependencies simultaneously within frames. With adversarial training, our method effectively reduces the unwanted artifacts in predictions, thereby ensuring the learning of more realistic and fluid human motions. The evaluation results indicate that AdvMT greatly enhances the accuracy of long-term predictions while also delivering robust short-term predictions

Seungwoo Jeong, Taekwon Ga, Inhwan Jeong et al.

In this study, we propose task planning framework for multiple robots that builds on a behavior tree (BT). BTs communicate with a data distribution service (DDS) to send and receive data. Since the standard BT derived from one root node with a single tick is unsuitable for multiple robots, a novel type of BT action and improved nodes are proposed to control multiple robots through a DDS asynchronously. To plan tasks for robots efficiently, a single task planning unit is implemented with the proposed task types. The task planning unit assigns tasks to each robot simultaneously through a single coalesced BT. If any robot falls into a fault while performing its assigned task, another BT embedded in the robot is executed; the robot enters the recovery mode in order to overcome the fault. To perform this function, the action in the BT corresponding to the task is defined as a variable, which is shared with the DDS so that any action can be exchanged between the task planning unit and robots. To show the feasibility of our framework in a real-world application, three mobile robots were experimentally coordinated for them to travel alternately to four goal positions by the proposed single task planning unit via a DDS.

Jeong-Hoon Lee, Jongeun Choi

Deep reinforcement learning has shown its effectiveness in various applications, providing a promising direction for solving tasks with high complexity. However, naively applying classical RL for learning a complex long-horizon task with a single control policy is inefficient. Thus, policy modularization tackles this problem by learning a set of modules that are mapped to primitives and properly orchestrating them. In this study, we further expand the discussion by incorporating simultaneous activation of the skills and structuring them into multiple hierarchies in a recursive fashion. Moreover, we sought to devise an algorithm that can properly orchestrate the skills with different action spaces via multiplicative Gaussian distributions, which highly increases the reusability. By exploiting the modularity, interpretability can also be achieved by observing the modules that are used in the new task if each of the skills is known. We demonstrate how the proposed scheme can be employed in practice by solving a pick and place task with a 6 DoF manipulator, and examine the effects of each property from ablation studies.

Kyubaek Yoon, Hojun You, Wei-Ying Wu et al.

In system identification, estimating parameters of a model using limited observations results in poor identifiability. To cope with this issue, we propose a new method to simultaneously select and estimate sensitive parameters as key model parameters and fix the remaining parameters to a set of typical values. Our method is formulated as a nonlinear least squares estimator with L1-regularization on the deviation of parameters from a set of typical values. First, we provide consistency and oracle properties of the proposed estimator as a theoretical foundation. Second, we provide a novel approach based on Levenberg-Marquardt optimization to numerically find the solution to the formulated problem. Third, to show the effectiveness, we present an application identifying a biomechanical parametric model of a head position tracking task for 10 human subjects from limited data. In a simulation study, the variances of estimated parameters are decreased by 96.1% as compared to that of the estimated parameters without L1-regularization. In an experimental study, our method improves the model interpretation by reducing the number of parameters to be estimated while maintaining variance accounted for (VAF) at above 82.5%. Moreover, the variances of estimated parameters are reduced by 71.1% as compared to that of the estimated parameters without L1-regularization. Our method is 54 times faster than the standard simplex-based optimization to solve the regularized nonlinear regression.