BioMorphic Intelligence Lab
Biologically inspired solutions for aerial robotics
Aerial robots are now ubiquitous. Thanks to their nimbleness, manoeuvrability, and affordability, drones are used in many sectors to monitor, map, and inspect. As a next step, flying robots offer more when interacting with their surroundings via anthropomorphic-like manipulation capabilities. Some overarching challenges remain for this new class of aerial robots, and solutions inspired by biology can be implemented across three key areas for robot performance: sensing their environment, processing this information, and acting upon the results.
SENSE
Bio-inspired perception (e.g., visual or tactile feedback) can provide the drone with information on its environment, mimicking animals’ sensory feedback. Using retina-like event cameras, drones can avoid obstacles and detect objects at a fraction of the power and latency of conventional hardware and algorithms. Enhancing tactile feedback can also prompt different behaviors in response to different force stimuli.
THINK
Bio-inspired, brain-like models from Neuromorphic AI can help lower the computational load and speed up sensory data processing for navigation. This boosts real-time control and autonomy. Compliance embedded in the control of the robot also favors safe and robust interaction with unknown environments and targets.
ACT
Bio-inspired design and materials make the drone's body fit for interaction with unknown objects and enable a safe response to external disturbances. Robot morphology can be inspired by flying animals’ shape, configuration, and materials. Together, these features create embodied intelligence and can partially offset the behavior complexity handled by the brain.
The BioMorphic Intelligence Lab aims to tackle robustness and efficiency challenges for interacting drones, using biologically inspired solutions for both the 'body' and the 'brain' and applying embodied intelligence and neuromorphic AI techniques.
The BioMorphic Intelligence Lab is part of the TU Delft AI Labs programme.
The Team
Directors
PhD students
Associated faculty
Education
Courses
2023/2024
2022/2023
- Fundamentals of AI | IFEEMCS520100
- Interdisciplinary Advanced AI Project | IFEEMCS520200
- Data Mining | CSE2525
- Joint interdisciplinary project | TUD4040
2021/2022
-
Capstone Applied AI Project | TI3150TU
2020/2021
- Final Project | ES5000
- RO Msc Thesis | RO57035
2019/2020
- Deep Learning | CS4240
- Research Project | CSE3000
- Computer Vision by Deep Learning | CS4245
- Machine Learning 2 | CS4230
- Computer Science program | IN5000
- Physical Intelligence for Interaction (Bio-inspired Intelligence and learning for Aerospace Applications) | AE4350
Master projects
Ongoing
- Time steps in spiking neural networks, Nergis Tomen, Alex de Los Santos Subirats (2023/2024)
- Self-organized criticality in spiking networks of non-leaky integrator neurons, Nergis Tomen, Luca Frattini (2023/2024)
- Autonomous Vision-guided Navigation in Forest Environments, Salua Hamaza, Andreas Zwanenburg (2022/2023)
- Biomorphic Whiskers for Aerial Wall Following, Salua Hamaza, Mahima Yoga (2022/2023)
- The Flying Manipulator: Active force balancing for fast aerial pick and place, Salua Hamaza, Michele Bianconi (2022/2023)
- Tactile Navigation for Free-flying Spacecraft, Salua Hamaza, Luke de Waal (2022/2023)
- Full Body Trajectory Optimization for Athletic Maneuvers with an Aerial Manipulator, Salua Hamaza, Rita Santos (2022/2023)
- Biomorphic Whiskers for Aerial Ceiling Following, Salua Hamaza, Nils de Kron (2022/2023)
- Aerial Tactile Servoing for Fruit Harvesting, Salua Hamaza, Anish Jadoenathmisier (2022/2023)
- Dynamic Balancing Manipulators for Drones, Salua Hamaza, Alexander Bom (2022/2023)
- NeuroBench: Benchmarking spiking and analog neural networks for primate tracking sata, Nergis Tomen, Paul Hueber (2022/2023)
Finished
- Automated Aerial Screwing with a Fully Actuated Aerial Manipulator, Salua Hamaza, Paul Reck (2022/2023)
- Vision-based Quadrotor Perching on Tree Branches, Salua Hamaza, Seamus McGinley (2022/2023)
- Simple Online Visual Object Tracker Fusion based on Distributed Kalman Filtering, Nergis Tomen, Yigen Zhong (2022/2023)
- Optimizing Event-Based Vision by Realizing Super-Resolution in Event-Space: an Experimental Approach, Nergis Tomen, Mahir Sabanoglu (2022/2023)
- Optical Flow Upsamplers Ignore Details: Neighborhood Attention Transformers for Convex Upsampling, Nergis Tomen, Sander Gielisse (2022/2023)
- Making It Clear Using Vision Transformers in Multi-View Stereo on Specular and Transparent Materials, Nergis Tomen, Pieter Tolsma (2022/2023)
- Battle the Wind: Improving Flight Stability of a Flapping Wing Micro Air Vehicle under Wind Disturbance, Salua Hamaza, Sunyi Wang (2021/2022)
- ADAPT: A 3 Degrees of Freedom Reconfigurable Force Balanced Parallel Manipulator for Aerial Applications, Salua Hamaza, Kartik Suryavansi (2021/2022)
- Sensorless Impedance Control for Curved Surface Inspections Using the Omni-Drone Aerial Manipulator, Salua Hamaza, Hani Abu-Jurji (2021/2022)
- Embodied airflow sensing for improved in-gust flight of flapping wing MAVs, Salua Hamaza, Chenyao Wang (2021/2022)
- A Centralised Approach to Aerial Manipulation on Overhanging Surfaces, Salua Hamaza, Martijn Brummelhuis (2020/2021)