Author name cluster

Beomjoon Kim

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

13 papers

2 author rows

ICRA Conference 2025 Conference Paper

PRESTO: Fast Motion Planning Using Diffusion Models Based on Key-Configuration Environment Representation

Mingyo Seo
Yoonyoung Cho
Yoonchang Sung
Peter Stone 0001
Yuke Zhu
Beomjoon Kim

We introduce a learning-guided motion planning framework that generates seed trajectories using a diffusion model for trajectory optimization. Given a workspace, our method approximates the configuration space (C-space) obstacles through an environment representation consisting of a sparse set of task-related key configurations, which is then used as a conditioning input to the diffusion model. The diffusion model integrates regularization terms that encourage smooth, collision-free trajectories during training, and trajectory optimization refines the generated seed trajectories to correct any colliding segments. Our experimental results demonstrate that high-quality trajectory priors, learned through our C-space-grounded diffusion model, enable the efficient generation of collision-free trajectories in narrow-passage environments, outperforming previous learning- and planning-based baselines. Videos and additional materials can be found on the project page: https://kiwi-sherbet.github.io/PRESTO.

Details

ICLR Conference 2024 Conference Paper

An Intuitive Multi-Frequency Feature Representation for SO(3)-Equivariant Networks

Dongwon Son
Jaehyung Kim 0001
Sanghyeon Son
Beomjoon Kim

The usage of 3D vision algorithms, such as shape reconstruction, remains limited because they require inputs to be at a fixed canonical rotation. Recently, a simple equivariant network, Vector Neuron (VN) has been proposed that can be easily used with the state-of-the-art 3D neural network (NN) architectures. However, its performance is limited because it is designed to use only three-dimensional features, which is insufficient to capture the details present in 3D data. In this paper, we introduce an equivariant feature representation for mapping a 3D point to a high-dimensional feature space. Our feature can discern multiple frequencies present in 3D data, which, as shown by Tancik et al. (2020), is the key to designing an expressive feature for 3D vision tasks. Our representation can be used as an input to VNs, and the results demonstrate that with our feature representation, VN captures more details, overcoming the limitation raised in its original paper.

Details

ICLR Conference 2024 Conference Paper

CORN: Contact-based Object Representation for Nonprehensile Manipulation of General Unseen Objects

Yoonyoung Cho
Junhyek Han
Yoontae Cho
Beomjoon Kim

Nonprehensile manipulation is essential for manipulating objects that are too thin, large, or otherwise ungraspable in the wild. To sidestep the difficulty of contact modeling in conventional modeling-based approaches, reinforcement learning (RL) has recently emerged as a promising alternative. However, previous RL approaches either lack the ability to generalize over diverse object shapes, or use simple action primitives that limit the diversity of robot motions. Furthermore, using RL over diverse object geometry is challenging due to the high cost of training a policy that takes in high-dimensional sensory inputs. We propose a novel contact-based object representation and pretraining pipeline to tackle this. To enable massively parallel training, we leverage a lightweight patch-based transformer architecture for our encoder that processes point clouds, thus scaling our training across thousands of environments. Compared to learning from scratch, or other shape representation baselines, our representation facilitates both time- and data-efficient learning. We validate the efficacy of our overall system by zero-shot transferring the trained policy to novel real-world objects. We highly recommend the video attached in the supplementary material. Code and videos are available at \url{https://sites.google.com/view/contact-non-prehensile}.

Details

ICRA Conference 2024 Conference Paper

Open X-Embodiment: Robotic Learning Datasets and RT-X Models: Open X-Embodiment Collaboration

Abby O'Neill
Abdul Rehman
Abhiram Maddukuri
Abhishek Gupta 0004
Abhishek Padalkar
Abraham Lee
Acorn Pooley
Agrim Gupta

Large, high-capacity models trained on diverse datasets have shown remarkable successes on efficiently tackling downstream applications. In domains from NLP to Computer Vision, this has led to a consolidation of pretrained models, with general pretrained backbones serving as a starting point for many applications. Can such a consolidation happen in robotics? Conventionally, robotic learning methods train a separate model for every application, every robot, and even every environment. Can we instead train "generalist" X-robot policy that can be adapted efficiently to new robots, tasks, and environments? In this paper, we provide datasets in standardized data formats and models to make it possible to explore this possibility in the context of robotic manipulation, alongside experimental results that provide an example of effective X-robot policies. We assemble a dataset from 22 different robots collected through a collaboration between 21 institutions, demonstrating 527 skills (160266 tasks). We show that a high-capacity model trained on this data, which we call RT-X, exhibits positive transfer and improves the capabilities of multiple robots by leveraging experience from other platforms. The project website is robotics-transformer-x. github.io.

Details

IROS Conference 2023 Conference Paper

Pre-and Post-Contact Policy Decomposition for Non-Prehensile Manipulation with Zero-Shot Sim-To-Real Transfer

Minchan Kim
Junhyek Han
Jaehyung Kim 0001
Beomjoon Kim

We present a system for non-prehensile manipulation that require a significant number of contact mode transitions and the use of environmental contacts to successfully manipulate an object to a target location. Our method is based on deep reinforcement learning which, unlike state-of-the-art planning algorithms, does not require apriori knowledge of the physical parameters of the object or environment such as friction coefficients or centers of mass. The planning time is reduced to the simple feed-forward prediction time on a neural network. We propose a computational structure, action space design, and curriculum learning scheme that facilitates efficient exploration and sim-to-real transfer. In challenging real-world non-prehensile manipulation tasks, we show that our method can generalize over different objects, and succeed even for novel objects not seen during training. Project website: https://sites.google.com/view/nonprenehsile-decomposition

Details

IROS Conference 2022 Conference Paper

Ω 2: Optimal Hierarchical Planner for Object Search in Large Environments via Mobile Manipulation

Yoonyoung Cho
Donghoon Shin
Beomjoon Kim

We propose a hierarchical planning algorithm that efficiently computes an optimal plan for finding a target object in large environments where a robot must simultaneously consider both navigation and manipulation. One key challenge that arises from large domains is the substantial increase in search space complexity that stems from considering mobile manipulation actions and the increase in number of objects. We offer a hierarchical planning solution that effectively handles such large problems by decomposing the problem into a set of low-level intra-container planning problems and a high-level key place planning problem that utilizes the low-level plans. To plan optimally, we propose a novel admissible heuristic function that, unlike previous methods, accounts for both navigation and manipulation costs. We propose two algorithms: one based on standard A* that returns the optimal solution, and the other based on Anytime Repairing A* (ARA*) which can trade-off computation time and solution quality, and prove they are optimal even when we use hierarchy. We show our method outperforms existing algorithms in simulated domains involving up to 6 times more number of objects than previously handled.

Details

AAAI Conference 2020 Conference Paper

Monte Carlo Tree Search in Continuous Spaces Using Voronoi Optimistic Optimization with Regret Bounds

Beomjoon Kim
Kyungjae Lee
Sungbin Lim
Leslie Kaelbling
Tomas Lozano-Perez

Many important applications, including robotics, data-center management, and process control, require planning action sequences in domains with continuous state and action spaces and discontinuous objective functions. Monte Carlo tree search (MCTS) is an effective strategy for planning in discrete action spaces. We provide a novel MCTS algorithm (VOOT) for deterministic environments with continuous action spaces, which, in turn, is based on a novel black-box function-optimization algorithm (VOO) to efﬁciently sample actions. The VOO algorithm uses Voronoi partitioning to guide sampling, and is particularly efﬁcient in highdimensional spaces. The VOOT algorithm has an instance of VOO at each node in the tree. We provide regret bounds for both algorithms and demonstrate their empirical effectiveness in several high-dimensional problems including two difﬁcult robotics planning problems.

PDF Details

AAAI Conference 2019 Conference Paper

Adversarial Actor-Critic Method for Task and Motion Planning Problems Using Planning Experience

Beomjoon Kim
Leslie Pack Kaelbling
Tomás Lozano-Pérez

We propose an actor-critic algorithm that uses past planning experience to improve the efficiency of solving robot task-and-motion planning (TAMP) problems. TAMP planners search for goal-achieving sequences of high-level operator instances specified by both discrete and continuous parameters. Our algorithm learns a policy for selecting the continuous parameters during search, using a small training set generated from the search trees of previously solved instances. We also introduce a novel fixed-length vector representation for world states with varying numbers of objects with different shapes, based on a set of key robot configurations. We demonstrate experimentally that our method learns more efficiently from less data than standard reinforcementlearning approaches and that using a learned policy to guide a planner results in the improvement of planning efficiency.

PDF Details

AAAI Conference 2018 Conference Paper

Guiding Search in Continuous State-Action Spaces by Learning an Action Sampler From Off-Target Search Experience

Beomjoon Kim
Leslie Kaelbling
Tomás Lozano-Pérez

In robotics, it is essential to be able to plan efﬁciently in highdimensional continuous state-action spaces for long horizons. For such complex planning problems, unguided uniform sampling of actions until a path to a goal is found is hopelessly inefﬁcient, and gradient-based approaches often fall short when the optimization manifold of a given problem is not smooth. In this paper, we present an approach that guides search in continuous spaces for generic planners by learning an action sampler from past search experience. We use a Generative Adversarial Network (GAN) to represent an action sampler, and address an important issue: search experience consists of a relatively large number of actions that are not on a solution path and a relatively small number of actions that actually are on a solution path. We introduce a new technique, based on an importance-ratio estimation method, for using samples from a non-target distribution to make GAN learning more data-efﬁcient. We provide theoretical guarantees and empirical evaluation in three challenging continuous robot planning problems to illustrate the effectiveness of our algorithm.

PDF Details

NeurIPS Conference 2018 Conference Paper

Regret bounds for meta Bayesian optimization with an unknown Gaussian process prior

Zi Wang
Beomjoon Kim
Leslie Kaelbling

Bayesian optimization usually assumes that a Bayesian prior is given. However, the strong theoretical guarantees in Bayesian optimization are often regrettably compromised in practice because of unknown parameters in the prior. In this paper, we adopt a variant of empirical Bayes and show that, by estimating the Gaussian process prior from offline data sampled from the same prior and constructing unbiased estimators of the posterior, variants of both GP-UCB and \emph{probability of improvement} achieve a near-zero regret bound, which decreases to a constant proportional to the observational noise as the number of offline data and the number of online evaluations increase. Empirically, we have verified our approach on challenging simulated robotic problems featuring task and motion planning.

PDF Details

ICRA Conference 2017 Conference Paper

Learning to guide task and motion planning using score-space representation

Beomjoon Kim
Leslie Pack Kaelbling
Tomás Lozano-Pérez

In this paper, we propose a learning algorithm that speeds up the search in task and motion planning problems. Our algorithm proposes solutions to three different challenges that arise in learning to improve planning efficiency: what to predict, how to represent a planning problem instance, and how to transfer knowledge from one problem instance to another. We propose a method that predicts constraints on the search space based on a generic representation of a planning problem instance, called score space, where we represent a problem instance in terms of performance of a set of solutions attempted so far. Using this representation, we transfer knowledge, in the form of constraints, from previous problems based on the similarity in score space. We design a sequential algorithm that efficiently predicts these constraints, and evaluate it in three different challenging task and motion planning problems. Results indicate that our approach perform orders of magnitudes faster than an unguided planner.

Details

RLDM Conference 2013 Conference Abstract

Approximate Policy Iteration with Demonstration Data

Beomjoon Kim
Amir-massoud Farahmand
Joelle Pineau
Doina Precup

We propose an algorithm to solve uncertain sequential decision-making problems that utilizes two different types of data sources. The first is the data available in the conventional reinforcement learning setup: an agent interacts with the environment and receives a sequence of state transition samples alongside the corresponding reward signal. The second data source, which differentiates the setup of this work from the usual reinforcement learning framework, is in the form of expert’s demonstrations, that is, a set of states with the expert’s suggested actions. Benefitting from both sources of data, which are available in many real-world application domains, allows the agent to perform well even with few data points. The algorithm is couched in the framework of Approxi- mate Policy Iteration. Its approximate policy evaluation step is formulated as a convex optimization problem in which the expert demonstration data act as a set of linear constraints. In a real robotic navigation task, we show that the algorithm outperforms both pure approximate policy iteration and supervised learning.

PDF Details

NeurIPS Conference 2013 Conference Paper

Learning from Limited Demonstrations

Beomjoon Kim
Amir-massoud Farahmand
Joelle Pineau
Doina Precup

We propose an approach to learning from demonstration (LfD) which leverages expert data, even if the expert examples are very few or inaccurate. We achieve this by integrating LfD in an approximate policy iteration algorithm. The key idea of our approach is that expert examples are used to generate linear constraints on the optimization, in a similar fashion to large-margin classification. We prove an upper bound on the true Bellman error of the approximation computed by the algorithm at each iteration. We show empirically that the algorithm outperforms both pure policy iteration, as well as DAgger (a state-of-art LfD algorithm) and supervised learning in a variety of scenarios, including when very few and/or imperfect demonstrations are available. Our experiments include simulations as well as a real robotic navigation task.

PDF Details