Sitemap
A list of all the posts and pages found on the site. For you robots out there, there is an XML version available for digesting as well.
Pages
Posts
Future Blog Post
Published:
This post will show up by default. To disable scheduling of future posts, edit config.yml and set future: false.
Blog Post number 4
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 3
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 2
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
Blog Post number 1
Published:
This is a sample blog post. Lorem ipsum I can’t remember the rest of lorem ipsum and don’t have an internet connection right now. Testing testing testing this blog post. Blog posts are cool.
portfolio
Open Source Repositories
- Fast Multi-robot Exploration
Decentralized multi-robot exploration framework for coordinating teams of UAVs in forest environments. - SMB Path Planner
Autonomous path planning pipeline deployed on the Super Mega Bot (SMB) platform during the ETH Zurich Robotics Summer School. - Multi-robot Coordination
A hierarchical global path-planning framework for multi-robot systems, enabling coordinated trajectory generation for fleets of Unmanned Aerial Vehicles (UAVs). - Pose-graph Backend
A multi-agent sensor fusion engine leveraging optimization-based pose-graph backends to support distributed multi-robot path planning. - Multirotors Landing
A deep reinforcement learning (RL) pipeline for autonomous multi-rotor UAV landing, leveraging multimodal semantic scene segmentation and depth inputs to identify safe landing zones. - Pointcloud Utilities
A collection of modular ROS nodes designed for real-time 3D point cloud processing, transformation, and spatial data handling.
B.Sc. Theses Projects
Published:
Projects carried out in the final stages of the B.Sc. in Mechanical Engineering:
- Study of dynamic behaviour of a Push-Rod Suspension.
- Design of a Kaplan Turbine for a medium-sized power plant.
- Design of the central crankshaft of drive motor MR 31 80 UP2A.
Calibration and Set-up of Two Independent Cameras Mounted on Servos for UAVs Relative Pose Estimation
Published:
Semester thesis project at Vision for Robotics Lab, ETH Zürich.
Supervised by Prof. Dr. Margarita Chli.
3D Radiation Mapping with a small UAV
Published:
Master’s thesis project at Vision for Robotics Lab, ETH Zürich.
Supervised by Prof. Dr. Margarita Chli.
publications
Active Learning for UAV-based Semantic Mapping
Published in Workshop on Informative Path Planning and Active Sampling, Robotics: Science and Systems (RSS), 2019
Addressing the labor-intensive bottleneck of training data collection in vision-based UAV applications, our novelty-aware path planner is validated on real-world terrain mapping datasets, yielding substantially smaller, more informative training datasets compared to standard lawnmower pattern collection.
A Fully-Integrated Sensing and Control System for High-Accuracy Mobile Robotic Building Construction
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2019
Implemented on a real platform under realistic construction conditions, the proposed system enables fully autonomous mobile manipulators to achieve sub-centimeter positioning accuracy using solely on-board sensing. Video available here.
Perception-aware Path Planning for UAVs using Semantic Segmentation
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
This paper presents a perception-aware path-planning pipeline for UAVs that leverages semantic segmentation to avoid texture-less or problematic areas, such as bodies of water, that degrade monocular VIO state estimation, actively steering the robot toward perceptually informative regions. Video available here.
Multi-robot Coordination with Agent-Server Architecture for Autonomous Navigation in Partially Unknown Environments
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2020
A server-agent system architecture for multi-robot autonomous navigation in partially unknown environments is presented, where computationally demanding tasks like global mapping and path planning are outsourced to a central server, while agents handle local pose estimation and obstacle avoidance onboard. Video available here.
Semantic-aware Active Perception for UAVs using Deep Reinforcement Learning
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021
The paper presents a semantic-aware path-planning pipeline for UAVs that uses deep reinforcement learning to evaluate the perceptual informativeness of visible semantic classes. By training on semantic cues across non-photorealistic, randomly generated scenes, the deep policy network successfully generalizes to unseen environments while guiding the UAV away from perceptually degraded regions. Video available here.
Informed Sampling Exploration Path Planner for 3D Reconstruction of Large Scenes
Published in IEEE Robotics and Automation Letters (RA-L), 2021
Addressing MAV computational and energy constraints, the letter proposes a frontier-based informed sampling approach streamlines viewpoint evaluation to accelerate autonomous exploration, outperforming state-of-the-art planners in both exploration speed and final 3D reconstruction quality. Video available here.
Fully Autonomous Live 3D Reconstruction with an MAV: Hardware- and Software-Setup
Published in Research Demos at International Conference on 3D Vision (3DV), 2021
The tutorial presents a versatile Micro-Aerial Vehicle (MAV) setup demonstrating fully autonomous live 3D reconstruction in real-world scenarios. With the aim of reproducability, the key information on both the hardware- and software-setup are provided. Video available here.
Autonomous Emergency Landing for Multicopters using Deep Reinforcement Learning
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
The paper presents an autonomous emergency landing pipeline for multicopters that handles critical failures, such as mechanical malfunctions, GPS jamming, or sudden battery drops. By leveraging semantic and depth representations, our policy achieves direct zero-shot transfer to the real world without requiring any additional fine-tuning. Video available here.
T-PRM: Temporal Probabilistic Roadmap for Path Planning in Dynamic Environments
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
Temporal-PRM maintains the core advantages of traditional PRM, such as multi-query capabilities and smooth path generation, while enabling collision-free navigation in highly dynamic, cluttered environments, operating in real time onboard a flying robot. Video available here.
Voxfield: Non-Projective Signed Distance Fields for Online Planning and 3D Reconstruction
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
Outperforming state-of-the-art methods in map coverage, accuracy, and processing speed, Voxfield operates effectively onboard compute-constrained micro-aerial vehicles (MAVs), generating accurate ESDF maps to enable real-time trajectory planning and obstacle avoidance. Video available here.
Decentralised Multi-Robot Exploration Using Monte Carlo Tree Search
Published in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022
Addressing real-world challenges in inspection and surveying, the proposed DMCE strategy enables efficient, decentralized multi-robot exploration across unknown environments, outperforming state-of-the-art planners and greedy baselines with up to a 30% reduction in exploration time. Video available here.
Sweep-Your-Map: Efficient Coverage Planning for Aerial Teams in Large-Scale Environments
Published in IEEE Robotics and Automation Letters (RA-L), 2022
This letter proposes a pipeline that generates structured task partitions to achieve comprehensive visual coverage significantly faster than state-of-the-art exploration baselines, addressing the strict battery and flight-time constraints of small drones in large-scale outdoor missions. Video available here.
Towards Robust Active Planning for Autonomous Aerial Navigation
Published in ETH Doctoral Examination, 2023
This thesis addresses the fundamental challenges of autonomous aerial navigation in GPS-denied and obstacle-dense environments across two core pillars: decentralized multi-robot coordination and semantic perception-aware active planning. By integrating high-level semantic scene understanding and deep reinforcement learning (RL) into path planning, the proposed frameworks improve localization reliability, mission execution speed, and robot safety in real-world scenarios.
Fast multi-UAV decentralized exploration of forests
Published in IEEE Robotics and Automation Letters (RA-L), 2023
Addressing the challenges of high obstacle density and long-distance wireless communication limits in UAV fleets, the proposed multi-robot exploration framework achieves complete coverage of complex forest environments up to 30% faster than state-of-the-art baselines. Video available here.
talks
Perception-aware Path Planning for UAVs using Semantic Segmentation
Published:
Presented the paper at the conference to an audience of scientific peers. The recorded talk is available here.
Multi-robot Coordination with Agent-Server Architecture for Autonomous Navigation in Partially Unknown Environments
Published:
Presented the paper at the conference to an audience of scientific peers. The recorded talk is available here.
Semantic-aware Active Perception for UAVs using Deep Reinforcement Learning
Published:
Presented the paper at the conference to an audience of scientific peers. The recorded talk is available here.
Autonomous Emergency Landing for Multicopters using Deep Reinforcement Learning
Published:
Presented the paper at the conference to an audience of scientific peers. The recorded talk is available here.
T-PRM: Temporal Probabilistic Roadmap for Path Planning in Dynamic Environments
Published:
Presented the paper at the conference to an audience of scientific peers. The recorded talk is available here.
teaching
ETH Robotics Summer School
Summer School, ETH Zürich, 2019
Organized and led the hands-on tutorial on path planning at the ETH Zürich Robotics Summer School from 2019 to 2022. The program brought together high-achieving Master’s and PhD researchers from world-renowned universities.
- Information about the summer school
- Slides
- Code
