We are now focusing on these fields:


Inspired by nature

Geckos are small lizards belonging to the infraorder Gekkota, found in warm climates throughout the world. They range from 1.6 to 60 cm (0.64 to 24 inches). Most geckos cannot blink, but they often lick their eyes to keep them clean and moist. They have a fixed lens within each iris that enlarges in darkness to let in more light.

The amazing adhesion of gecko pads to almost any kind of surfaces has inspired a very active research direction over the last decade: the investigation of how geckos achieve this feat and how this knowledge can be turned into new strategies to reversibly join surfaces.

In our research, we are focusing on gecko-inspired adhesive pads and their applications.
Read more about Gecko

Origami and 3D Printing

Inspired by the art of paper-folding

Origami (折り紙, Japanese pronunciation: [oɾiɡami], from ori meaning “folding”, and kami meaning “paper” (kami changes to gami due to rendaku)) is the art of paper folding, which is often associated with Japanese culture. In modern usage, the word “origami” is used as an inclusive term for all folding practices, regardless of their culture of origin. The goal is to transform a flat square sheet of paper into a finished sculpture through folding and sculpting techniques. Modern origami practitioners generally discourage the use of cuts, glue, or markings on the paper. Origami folders often use the Japanese word kirigami to refer to designs which use cuts.

Structures with origami design enable objects to transform into various three-dimensional shapes. In our research we are focusing on origami-inspired functional structures. (e.g. robotic gripper, pneumatic actuators.)
Read more about Origami

Robot Learning

Learning intelligence from data

Robot learning is a research field at the intersection of machine learning and robotics. It studies techniques allowing a robot to acquire novel skills or adapt to its environment through data-driven learning. The embodiment of the robot, situated in a physical embedding, provides at the same time specific difficulties and opportunities for guiding the learning process.

Our research mostly lies in perception and planning problems in the physical world, including robotic planning under physical interaction, autonomous driving under social interaction, etc. We are dedicated to developing robust, efficient and interpretable frameworks for our perception & planning modules.

Read more about Robot Learning

Finger Vision

Simulating human senses

Tactile sensing is essential to the human perception system, so as to robot. In this paper, we develop a novel optical-based tactile sensor “FingerVision” with effective signal processing algorithms.

This sensor is composed of soft skin with embedded marker array bonded to rigid frame, and a web camera with a fisheye lens. While being excited with contact force, the camera tracks the movements of markers and deformation field is obtained. Compared to existing tactile sensors, our sensor features compact footprint, high resolution, and ease of fabrication.

Topology Optimization

Optimize Engineering Structures Automatically

Topology optimization (TO) is a mathematical method that optimizes material layout within a given design space, for a given set of loads, boundary conditions and constraints with the goal of maximizing the performance of the system. TO is different from shape optimization and sizing optimization in the sense that the design can attain any shape within the design space, instead of dealing with predefined configurations.

The conventional TO formulation uses a finite element method (FEM) to evaluate the design performance. The design is optimized using either gradient-based mathematical programming techniques such as the optimality criteria algorithm and the method of moving asymptotes or non gradient-based algorithms such as genetic algorithms.

Our group are now focusing on B-spline based topology optimization and its applicatons.