Frontier Research Overview
How can brain-like mechanisms be developed and realized on artificial systems so they can perform multiple complex functions as biological living systems?
To address this fundamental question, we employ a bio-inspired approach to develop brain-like mechanisms for adaptive motor control and autonomous learning of embodied multi-sensorimotor robotic systems. The developed mechanisms (BRAIN technology) are adaptive and flexible, which can be transferred to application areas like human-machine interaction, brain-machine interface, and rehabilitation.
Further information: click!
Research Highlights
2022
Nature-Inspired Machine Intelligence: From Animals to Robots
GRAB: GRAdient-Based Shape-Adaptive Locomotion Control
Adaptive systems enable legged robots to cope with a wide range of environmental settings and unforeseen events. Existing reactive methods adapt either the walking frequency or the amplitude to only simple perturbations. This letter proposes an adaptive mechanism for central pattern generator (CPG)-based locomotion control that online-reacts to both internal and external soft constraints by adapting both the frequency and amplitude of driving signals. Our approach, namely GRAdient-Based shape adaptive control (GRAB), utilises real-time sensory signals for adapting the dynamics of the CPG. GRAB reacts to locomotion soft constraints given in a loss function. It can quickly adapt CPG’s dynamics variables to reduce such a loss, with a gradient-descent-like update step. The update perturbs the shape of the driving signal, which implicitly changes both frequency and amplitude of the robot locomotion pattern. We test the GRAB mechanism on a hexapod robot and its simulation, where we demonstrate its several benefits over a state-of-the-art adaptive control baseline. First, we show that it can be used for reducing the tracking error by simultaneously changing the walking amplitude and frequency. Also, GRAB can be used for limiting the maximum torque/current, preventing motor damage from unexpected perturbations. Finally, we demonstrate how GRAB can be utilised to naturally adjust the robot’s walking speed while taking into account multiple constraints, including target walking speed, external weight perturbations, and the robot’s physical limit. A video of this research.
For more details, see Phodapol et al., ICRA/RAL, 2022.
Continuous Online Adaptation of Bioinspired Adaptive Neuroendocrine Control of Autonomous Walking Robots
We developed an advanced control method with short-term memory for complex locomotion and lifelong adaptation of autonomous walking robots. The control method is inspired by a locomotion control strategy used by walking animals like cats, in which they use their short-term visual memory to detect an obstacle and take proactive steps to avoid colliding it. Using this control method allows a hexapod robot to traverse complex terrains and perform proactive leg movements to swing over an obstacle before hitting it. This robot control technology will increase the robot’s agility for real-world applications. A video of this research.
For more details, see Homchanthanakul et al., IEEE TNNLS, 2021.
Gait Adaptation of a Dung Beetle Rolling a Ball up a Slope
A previous study describes the gait pattern of the ball rolling behavior on flat terrain, but little is known how the dung beetles adapt their movement to roll a ball up a slope. Thus, in this work, we perform a visual investigation of dung beetles’ ball rolling behavior on 0 and 20-degree slopes and perform statistical analysis on the gait patterns to identify how dung beetles adapt their movement to roll a ball up a slope. We found that the dung beetle’s front legs and hind legs tend to stay in contact with the ground and dung ball more often in the 20-degree slope than in the 0-degree slope condition. A video of this research talk.
2020
Rules for the Leg Coordination of Dung Beetle Ball Rolling Behaviour
The dung beetle is particularly strong insect that can transport a large and heavy dung ball across the savanna. Through behavioral experiments and statistical analysis, we successfully reveal the secret rules that dung beetles use to transport a ball. This study can be used as a basis to push robot technology beyond the state of the art; thereby creating a next-generation robot with agility and versatility. “Imagine if we could build a similarly effective robot that could walk and transport an object ten times its own weight, like the beetle”.
For more details, see Leung et al., Scientific Reports, 2020.
A video link of the dung beetle experiments
Dynamical State Forcing on Central Pattern Generators
Many CPG-based locomotion models have a problem known as the tracking error problem, where the mismatch between the CPG driving signal and the state of the robot can cause undesirable behaviors for legged robots. Towards alleviating this problem, we introduce a mechanism that modulates the CPG signal using the robot’s interoceptive information. The key concept is to generate a driving signal that is easier for the robot to follow, yet can drive the locomotion of the robot. This can be done by nudging the CPG signal in the direction of lower tracking error, which can be analytically calculated. Unlike other reactive CPG, the proposed method does not rely on any parametric learning ability to adjust the shape of the signal, making it a unique option for a biological adaptive motor control.
For more details, see Chuthong et al., ICONIP 2020. Lecture Notes in Computer Science, 2020.
Video link:
2018
Modular Neural Control for Bio-Inspired Walking and Ball Rolling of a Dung Beetle-Like Robot
Dung beetles can perform impressive multiple motor behaviors using their legs. The behaviors include walking and rolling a large dung ball on different terrains, e.g., level ground and different slopes. To achieve such complex behaviors for legged robots, we propose here a modular neural controller for dung beetle-like locomotion and object transportation behaviors of a dung beetle-like robot. The modular controller consists of several modules based on three generic neural modules. The main modules include 1) a neural oscillator network module (as a central pattern generator (CPG)), 2) a neural CPG postprocessing module (PCPG), 3) a velocity regulating network module (VRN). The CPG generates basic rhythmic patterns. The patterns are first shaped by the PCPG and their amplitudes as well as phases are later modified by the VRN to obtain proper motor patterns for locomotion and object transportation. Combining all these neural modules, we can achieve different motor patterns for four different actions which are forward walking, backward walking, levelground ball rolling, and sloped-ground ball rolling. All these actions can be activated by four input neurons. The experimental results show that the simulated dung beetle-like robot can robustly perform the actions. The average forward speed is 0.058 cm/s and the robot is able to roll a large ball (about 3 times of its body height and 2 times of its weight) up different slope angles up to 25 degrees.
For more details, see Leung et al., ALIFE., 2018.