- Modular Robots and Swarm Intelligence
- Evolutionary Algorithms and Applications
- Reinforcement Learning in Robotics
- Robotic Path Planning Algorithms
- Distributed Control Multi-Agent Systems
- Biomimetic flight and propulsion mechanisms
- Robotics and Sensor-Based Localization
- Robotic Locomotion and Control
- Micro and Nano Robotics
- Advanced Sensor and Energy Harvesting Materials
- UAV Applications and Optimization
- Neural dynamics and brain function
- Soft Robotics and Applications
- Robot Manipulation and Learning
- Evolutionary Game Theory and Cooperation
- Advanced Materials and Mechanics
- Neural Networks and Applications
- Advanced Vision and Imaging
- Advanced Memory and Neural Computing
- Metaheuristic Optimization Algorithms Research
- Tactile and Sensory Interactions
- Insect and Arachnid Ecology and Behavior
- Evolution and Genetic Dynamics
- Teleoperation and Haptic Systems
- Aerospace Engineering and Energy Systems
École Polytechnique Fédérale de Lausanne
2016-2025
ETH Zurich
2024
University of Electro-Communications
2024
École Polytechnique
2006-2023
Yale University
2023
University of Twente
2023
Osaka University
2023
George Mason University
2023
Laboratoire de Biologie et Pharmacologie Appliquée
2021
Université Paris-Saclay
2021
Numerous methods have been developed for inferring gene regulatory networks from expression data, however, both their absolute and comparative performance remain poorly understood. In this paper, we introduce a framework critical assessment of network inference. We present an in silico benchmark suite that provided as blinded, community-wide challenge within the context DREAM (Dialogue on Reverse Engineering Assessment Methods) project. assess 29 gene-network-inference methods, which applied...
A highly versatile soft gripper that can handle an unprecedented range of object types is developed based on a new design dielectric elastomer actuators employing interdigitated electrode geometry, simultaneously maximizing both electroadhesion and electrostatic actuation while incorporating self-sensing. The multifunctionality the actuator leads to integrated, lightweight, fast, with simplified structure control. As service our authors readers, this journal provides supporting information...
Abstract Motivation: Over the last decade, numerous methods have been developed for inference of regulatory networks from gene expression data. However, accurate and systematic evaluation these is hampered by difficulty constructing adequate benchmarks lack tools a differentiated analysis network predictions on such benchmarks. Results: Here, we describe novel comprehensive method in silico benchmark generation performance profiling available to community as an open-source software called...
Reverse engineering methods are typically first tested on simulated data from in silico networks, for systematic and efficient performance assessment, before an application to real biological networks. In this paper, we present a method generating biologically plausible which allow realistic assessment of network inference algorithms. Instead using random graph models, known only partly capture the structural properties generate structures by extracting modules interaction Using yeast...
In this paper we describe the evolution of a discrete-time recurrent neural network to control real mobile robot. all our experiments evolutionary procedure is carried out entirely on physical robot without human intervention. We show that autonomous development set behaviors for locating battery charger and periodically returning it can be achieved by lifting constraints in design robot/environment interactions were employed preliminary experiment. The emergent homing behavior based an...
Swarm robotics systems are characterized by decentralized control, limited communication between robots, use of local information, and emergence global behavior. Such have shown their potential for flexibility robustness [1]-[3]. However, existing swarm large still to displaying simple proof-of-concept behaviors under laboratory conditions. It is our contention that one the factors holding back research almost universal insistence on homogeneous system components. We believe designers must...
In most animal species, vision is mediated by compound eyes, which offer lower resolution than vertebrate single-lens but significantly larger fields of view with negligible distortion and spherical aberration, as well high temporal in a tiny package. Compound eyes are ideally suited for fast panoramic motion perception. Engineering miniature artificial eye challenging because it requires accurate alignment photoreceptive optical components on curved surface. Here, we describe unique design...
Jumping can be a very efficient mode of locomotion for small robots to overcome large obstacles and travel in natural, rough terrain. In this paper we present the development characterization novel 5 cm, 7g jumping robot. It jump more than 27 times its own size outperforms existing by one order magnitude with respect height per weight size. employs elastic elements four bar linkage leg system allow powerful jumps adjustment force, take-off angle force profile during acceleration phase.
This article presents the design, fabrication, and characterization of a soft biomimetic robotic fish based on dielectric elastomer actuators (DEAs) that swims by body and/or caudal fin (BCF) propulsion. BCF is promising locomotion mechanism potentially offers swimming at higher speeds acceleration rates, efficient locomotion. The robot consists laminated silicone layers wherein two DEAs are used in an antagonistic configuration, generating undulating fish-like motion. design guided...
Abstract The advent of soft robotics has led to the development devices that harness compliance and natural deformability media with nonlinear elasticity. This a need batch‐manufacturable sensors can sustain large strains maintain kinematic compatibility systems they track. In this article, an approach address challenge is presented highly stretchable strain operate at up 500%. consist carbon black‐filled elastomer composite batch manufactured using film‐casting techniques CO 2 laser...
Abstract Robotic technologies, whether they are remotely operated vehicles, autonomous agents, assistive devices, or novel control interfaces, offer many promising capabilities for deployment in real‐world environments. Postdisaster scenarios a particularly relevant target applying such due to the challenging conditions faced by rescue workers and possibility increase their efficacy while decreasing risks face. However, field‐deployable technologies work have requirements robustness, speed,...
The recent advances in state estimation, perception, and navigation algorithms have significantly contributed to the ubiquitous use of quadrotors for inspection, mapping, aerial imaging. To further increase versatility quadrotors, works investigated an adaptive morphology, which consists modifying shape vehicle during flight suit a specific task or environment. However, these either complexity platform decrease its controllability. In this letter, we propose novel, simpler, yet effective...
Materials with controllable stiffness are of great interest to many fields, including medicine and robotics. In this paper we develop a new type variable material based on the combination rigid low-melting-point-alloy (LMPA) microstructure embedded in soft poly(dimethylsiloxane) (PDMS). This can transition between states by controlling phase LMPA through efficient, direct Joule-heating microstructure. The devices tested demonstrate relative change >25× (elastic modulus is 40 MPa when solid...
A novel variable stiffness actuator composed of a dielectric elastomer (DEA) and low-melting-point-alloy (LMPA) embedded silicone substrate is demonstrated. The device which we call (VSDEA) enables functional soft robots with simplified structure, where the DEA generates bending actuation LMPA provides controllable between rigid states by Joule heating. entire structure VSDEA made silicones an elastic modulus less than 1 MPa providing high compliance when active. has dimension 40 mm length ×...
This paper reports experimental results on self-organizing wireless networks carried by small flying robots. Flying ad hoc (FANETs) composed of unmanned aerial vehicles (UAVs) are flexible, inexpensive and fast to deploy. makes them a very attractive technology for many civilian military applications. Due the high mobility nodes, maintaining communication link between UAVs is challenging task. The topology these more dynamic than that typical mobile (MANETs) vehicle (VANETs). As consequence,...
A variable stiffness fiber made of silicone and low melting point alloys quickly becomes >700 times softer >400 more deformable when heated above 62 °C. It shows remarkable self-healing properties can be clamped, knitted, bonded, as shown in a foldable multi-purpose drone, wearable cast for bone injuries, soft multi-directional actuator.
Abstract In minimally invasive surgery, such as cardiac ablation, magnetically steered catheters made of variable‐stiffness materials can enable higher dexterity and force application to human tissue. However, the long transition time between soft rigid states leads a significant increase in procedure duration. Here, fast‐response, multisegmented catheter is described for surgery thread (FRVST) that encapsulates helical cooling channel. The rapid stiffness change FRVST, composed nontoxic...