We are DTETI Intelligent Robotic Lab

DTETI UGM Intelligent Robotic Lab is a cutting-edge research facility at Universitas Gadjah Mada dedicated to advancing the fields of robotics and artificial intelligence. Our lab brings together experts and emerging talent to pioneer innovative robotic systems that seamlessly integrate advanced AI techniques. We focus on developing autonomous systems, machine learning algorithms, and intelligent control strategies to tackle complex real-world challenges. At the heart of our research is the drive to create smart, adaptive robots capable of operating in diverse environments—from industrial automation to service applications. Our interdisciplinary team collaborates closely across domains such as computer vision, data analytics, and human-robot interaction, ensuring that our projects not only push technological boundaries but also offer practical, impactful solutions.

Research & Publications

Globally Optimal Intensity-Geometry ICP for Robust LiDAR Odometry

Igi Ardiyanto (Universitas Gadjah Mada), Mahmud Iwan Solihin (UCSI University, Malaysia),
12th International Conference on Control, Automation and Robotics, Nagoya, Japan, April 2026 To appear

Branch-and-Bound optimization framework for intensity-geometry enhanced point cloud registration that guarantees global convergence on the Special Euclidean group SE(3)

LORNet: lightweight unstructured off-road segmentation on embedded devices for mobile robotic and intelligent vehicle

Igi Ardiyanto (Universitas Gadjah Mada), Mako Takahama (Toyohashi University of Technology, Japan), Jun Miura (Toyohashi University of Technology, Japan),
Journal of Real-time Image Processing, Springer, Jan 2026 New Journal Paper

A lightweight unstructured off-road segmentation model specifically engineered to operate efficiently on embedded systems with minimal computational resources

Robust 3D LIDAR Point Cloud Registration Using Uncertainty-Aware Generalized Iterative Closest Point with Voxel-Based Efficiency

Igi Ardiyanto (Universitas Gadjah Mada),
17th International Conference on Information Technology and Electrical Engineering, Bangkok, Thailand, Oct 2025 Best Paper Award !!!

Enhancing 3D LIDAR Point Cloud registration through three synergistic components: (1) a physics-based spatial variance term modeling LIDAR uncertainty, (2) hierarchical outlier rejection, and (3) covariance-preserving voxelization

Sampling-Based Safety-Critical Control for Planar Quadrotors with Suspended Payloads

Igi Ardiyanto (Universitas Gadjah Mada), Hanung Adi Nugroho (Universitas Gadjah Mada), Mahmud Iwan Solihin (UCSI University, Malaysia),
International Journal of Control, Automation, and Systems (IJCAS), Springer, Sept 2025

Integrating Control Barrier Functions (CBFs), chance constraints, and Model Predictive Path Integral (MPPI) control for planar quadrotor with suspended payloads

Navigating Vision-based Autonomous Excavator Robot Using Deep Reinforcement Learning

Andhika Indra Laksana (Universitas Gadjah Mada), Ahmad Ataka A (Universitas Gadjah Mada), Igi Ardiyanto (Universitas Gadjah Mada), Prapto Nugroho (Universitas Gadjah Mada), Naufal Muafi (Universitas Gadjah Mada), Muhammad Rizqi Subeno (Universitas Gadjah Mada),
2025 12th International Conference on Electrical Engineering, Computer Science and Informatics (EECSI), Semarang, Indonesia, Sept 2025

Teleoperated excavator robots face significant challenges when performing digging tasks in hazardous environments, especially due to unstable signals and high latency. These limitations hinder the robot’s precision and responsiveness. Therefore, this research aims to develop an autonomous excavator robot system to overcome these issues.

Quadruped Locomotion and Navigation Under Uncertainty

Igi Ardiyanto (Universitas Gadjah Mada),
Research On Progress, DTETI Intelligent Robotic Lab, 2025

Quadruped locomotion and navigation with unmodeled payloads and uneven terrains

Adaptive 3D Growing Robot Navigation in Unstructured Environments Using Deep Reinforcement Learning

Febrial Farabi (Universitas Gadjah Mada), Ahmad Ataka A (Universitas Gadjah Mada), Igi Ardiyanto (Universitas Gadjah Mada),
2025 IEEE International Conference on Artificial Intelligence and Mechatronics Systems (AIMS), Sumedang, Indonesia, May 2025

This study proposes a Deep Q-Network (DQN)-based approach to control a segmented soft growing robot in a 3D simulated environment with dynamic targets and static obstacles.

Eikonal Model Predictive Path Integral for Risk-Aware Mobile Robot Navigation

Igi Ardiyanto (Universitas Gadjah Mada), Eka Firmansyah (Universitas Gadjah Mada),
11th International Conference on Control, Automation and Robotics, Kyoto, Japan, April 2025

Integrating the Eikonal-based cost map into a Model Predictive Path Integral

Lightweight monocular depth estimation network for robotics using intercept block GhostNet

Igi Ardiyanto (Universitas Gadjah Mada), Resha Dwika Hefni Al-Fahsi (Universitas Gadjah Mada),
Signal Image Video Processing, Springer, Jan 2025

A novel deep learning approach for monocular depth estimation with fewer computational and memory resources

Attitude control of UAV bicopter using adaptive LQG

Fahmizal (Universitas Gadjah Mada), Hanung Adi Nugroho (Universitas Gadjah Mada), Adha Imam Cahyadi (Universitas Gadjah Mada), Igi Ardiyanto (Universitas Gadjah Mada),
Results in Control and Optimization, Elsevier, Dec 2024

Linear Quadratic Gaussian (LQG) adaptive controller to control the attitude of the bicopter with uncertain payload conditions

Optimizing Maritime Vessel Trajectory Prediction Using Space-Based AIS Data and PSO-BiGRU

Dicka Ariptian Rahayu (National Research and Innovation Agency), Widyawan (Universitas Gadjah Mada), Igi Ardiyanto (Universitas Gadjah Mada), Wahyudi Hasbi (National Research and Innovation Agency),
IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, Yogyakarta, Indonesia, Nov 2024

An approach for predicting maritime vessel trajectories in the Seas around Papua Island, East Indonesia, leveraging space-based Automatic Identification System (AIS) data from LAPAN satellites

A streamlined approach for intelligent ship object detection using EL-YOLO algorithm

Defu Yang (UCSI University, Malaysia), Mahmud Iwan Solihin (UCSI University, Malaysia), Igi Ardiyanto (Universitas Gadjah Mada), Yawen Zhao (UCSI University, Malaysia), Bingyu Cai (UCSI University, Malaysia), Chaoran Chen (UCSI University, Malaysia),
Scientific Reports, Nature, July 2024

EL-YOLO (Efficient Lightweight You Only Look Once) algorithm based on YOLOv8, designed specifically for intelligent ship object detection

Off-Policy Adversarial Inverse Reinforcement Learning in Mobile Robot Navigation Task

Muhammad Rizqi Subeno (Universitas Gadjah Mada), Ahmad Ataka (Universitas Gadjah Mada), Igi Ardiyanto (Universitas Gadjah Mada), Adha Imam Cahyadi (Universitas Gadjah Mada),
IEEE International Conference on Artificial Intelligence and Mechatronics Systems, Yogyakarta, Indonesia, Feb 2024

An AIRL algorithm for reward learners to improve the RL algorithm to get an optimal policy for mobile robot navigation tasks