Sung-Kyun Kim — accepted AI-conference papers

2025

Enter the Mind Palace: Reasoning and Planning for Long-term Active Embodied Question Answering

Muhammad Fadhil Ginting, Dong-Ki Kim, Xiangyun Meng, Andrzej Marek Reinke, Bandi Jai Krishna, Navid Kayhani +7

CoRL 2025poster

As robots become increasingly capable of operating over extended periods—spanning days, weeks, and even months—they are expected to accumulate knowledge of their environments and leverage this experience to assist humans more effectively. This paper studies the problem of Long-term Active Embodied Q…

Cited by 0 Source ↗Scholar ↗

2025

SayComply: Grounding Field Robotic Tasks in Operational Compliance Through Retrieval-Based Language Models

Muhammad Fadhil Ginting, Dong-Ki Kim, Sung-Kyun Kim, Bandi Jai Krishna, Mykel J. Kochenderfer, Shayegan Omidshafiei +1

ICRA 2025

This paper addresses the problem of task planning for robots that must comply with operational manuals in real-world settings. Task planning under these constraints is essential for enabling autonomous robot operation in domains that require adherence to domain-specific knowledge. Current methods fo

Cited by 6 Source ↗code ↗Scholar ↗

2024

SEEK: Semantic Reasoning for Object Goal Navigation in Real World Inspection Tasks

Muhammad Fadhil Ginting, Sung-Kyun Kim, David Fan, Matteo Palieri, Mykel Kochenderfer, Ali-akbar Agha-mohammadi

RSS 2024poster

This paper addresses the problem of object-goal navigation in autonomous inspections in real-world environments. Object-goal navigation is crucial to enable effective inspections in various settings, often requiring the robot to identify the target object within a large search space. Current object…

Cited by 8 Source ↗PDF ↗Scholar ↗

2024

Semantic Belief Behavior Graph: Enabling Autonomous Robot Inspection in Unknown Environments

Muhammad Fadhil Ginting, David D. Fan, Sung-Kyun Kim, Mykel J. Kochenderfer, Ali-Akbar Agha-Mohammadi

IROS 2024poster

This paper addresses the problem of autonomous robotic inspection in complex and unknown environments. This capability is crucial for efficient and precise inspections in various real-world scenarios, even when faced with perceptual uncertainty and lack of prior knowledge of the environment. Existin…

Cited by 5 Source ↗Scholar ↗

2023

Fast and Scalable Signal Inference for Active Robotic Source Seeking

Christopher E. Denniston, Oriana Peltzer, Joshua Ott, Sangwoo Moon, Sung-Kyun Kim, Gaurav S. Sukhatme +3

ICRA 2023poster

In active source seeking, a robot takes repeated measurements in order to locate a signal source in a cluttered and unknown environment. A key component of an active source seeking robot planner is a model that can produce estimates of the signal at unknown locations with uncertainty quantification.…

Cited by 9 Source ↗Scholar ↗

2023

Safe and Efficient Navigation in Extreme Environments using Semantic Belief Graphs

Muhammad Fadhil Ginting, Sung-Kyun Kim, Oriana Peltzer, Joshua Ott, Sunggoo Jung, Mykel J. Kochenderfer +1

ICRA 2023poster

To achieve autonomy in unknown and unstruc-tured environments, we propose a method for semantic-based planning under perceptual uncertainty. This capability is cru-cial for safe and efficient robot navigation in environment with mobility-stressing elements that require terrain-specific locomotion po…

Cited by 8 Source ↗Scholar ↗

2023

Semantics-Aware Mission Adaptation for Autonomous Exploration in Urban Environments

Sangwoo Moon, Oriana Peltzer, Joshua Ott, Sung-Kyun Kim, Ali-Akbar Agha-Mohammadi

IROS 2023poster

Robust mission planning is an essential component for mission autonomy to perform complicated tasks in extreme environments. In this paper, we are interested in the role of semantic abstractions for guiding autonomous mission planning. In particular, we focus on how semantics can be leveraged to tra…

Cited by 3 Source ↗Scholar ↗

2022

ACHORD: Communication-Aware Multi-Robot Coordination With Intermittent Connectivity

Maira Saboia, Lillian Clark, Vivek Thangavelu, Jeffrey A. Edlund, Kyohei Otsu, Gustavo J. Correa +13

RA-L 2022

Communication is an important capability for multi-robot exploration because (1) inter-robot communication (comms) improves coverage efficiency and (2) robot-to-base comms improves situational awareness. Exploring comms-restricted (e.g., subterranean) environments requires a multi-robot system to to

Cited by 35 Source ↗Scholar ↗

2022

Adaptive Coverage Path Planning for Efficient Exploration of Unknown Environments

Amanda Bouman, Joshua Ott, Sung-Kyun Kim, Kenny Chen, Mykel J. Kochenderfer, Brett Lopez +2

IROS 2022poster

We present a method for solving the coverage problem with the objective of autonomously exploring an unknown environment under mission time constraints. Here, the robot is tasked with planning a path over a horizon such that the accumulated area swept out by its sensor footprint is maximized. Becaus…

Cited by 15 Source ↗Scholar ↗

2022

FIG-OP: Exploring Large-Scale Unknown Environments on a Fixed Time Budget

Oriana Peltzer, Amanda Bouman, Sung-Kyun Kim, Ransalu Senanayake, Joshua Ott, Harrison Delecki +5

IROS 2022poster

We present a method for autonomous exploration of large-scale unknown environments under mission time con-straints. We start by proposing the Frontloaded Information Gain Orienteering Problem (FIG-OP) - a generalization of the traditional orienteering problem where the assumption of a reliable envir…

Cited by 22 Source ↗Scholar ↗

2020

Autonomous Spot: Long-Range Autonomous Exploration of Extreme Environments with Legged Locomotion

Amanda Bouman, Muhammad Fadhil Ginting, Nikhilesh Alatur, Matteo Palieri, David D. Fan, Thomas Touma +5

IROS 2020poster

This paper serves as one of the first efforts to enable large-scale and long-duration autonomy using the Boston Dynamics Spot robot. Motivated by exploring extreme environments, particularly those involved in the DARPA Subterranean Challenge, this paper pushes the boundaries of the state-of-practice…

Cited by 198 Source ↗Scholar ↗

2020

Planning, Learning and Reasoning Framework for Robot Truck Unloading

Fahad Islam, Anirudh Vemula, Sung-Kyun Kim, Andrew Dornbush, Oren Salzman, Maxim Likhachev

ICRA 2020poster

We consider the task of autonomously unloading boxes from trucks using an industrial manipulator robot. There are multiple challenges that arise: (1) real-time motion planning for a complex robotic system carrying two articulated mechanisms, an arm and a scooper, (2) decision-making in terms of what…

Cited by 21 Source ↗Scholar ↗

2019

Bi-Directional Value Learning for Risk-Aware Planning Under Uncertainty

Sung-Kyun Kim, Rohan Thakker, Ali-Akbar Agha-Mohammadi

RA-L 2019

Decision-making under uncertainty is a crucial ability for autonomous systems. In its most general form, this problem can be formulated as a partially observable Markov decision process (POMDP). The solution policy of a POMDP can be implicitly encoded as a value function. In partially observable set

Cited by 36 Source ↗Scholar ↗

2019

Escaping Local Minima in Search-Based Planning using Soft Duplicate Detection

Wei Du, Sung-Kyun Kim, Oren Salzman, Maxim Likhachev

IROS 2019poster

Search-based planning for relatively low-dimensional motion-planning problems such as for autonomous navigation and autonomous flight has been shown to be very successful. Such framework relies on laying a grid over a state-space and constructing a set of actions (motion primitives) that connect the…

Cited by 12 Source ↗Scholar ↗

2017

Parts assembly planning under uncertainty with simulation-aided physical reasoning

Sung-Kyun Kim, Maxim Likhachev

ICRA 2017poster

Parts assembly, in a broad sense, is to make multiple objects to be in specific relative poses in contact with each other. One of the major reasons that make it difficult is uncertainty. Because parts assembly involves physical contact between objects, it requires higher precision than other manipul…

Cited by 11 Source ↗Scholar ↗

2016

Planning for grasp selection of partially occluded objects

Sung-Kyun Kim, Maxim Likhachev

ICRA 2016

In a cluttered scene, an object is often occluded by other objects, and a robot cannot figure out what the object is and perceive its pose exactly. We assume that the robot is equipped with a depth sensor and given a database of 3D object models and their grasping poses, but yet there is uncertainty

Cited by 18 Source ↗Scholar ↗