News
AIRS's 19 papers accepted by ICRA 2021
ICRA (International Conference on Robotics and Automation) is one of the top conferences in the field of robotics. According to the conference statistics, there were 4,056 submissions this year. Overall, 4,005 papers were reviewed: 2,766 for ICRA 2021 and 1,239 for the IEEE Robotics and Automation Letters (RA-L). 1,946 were selected for presentation, among which 19 papars were from AIRS.
Some of the accepted papers will be introduced below.
1. RigidFusion: Robot Localisation and Mapping in Environments with Large Dynamic Rigid Objects (RA-L)
This work presents a novel RGB-D SLAM approach to simultaneously segment, track and reconstruct the static background and large dynamic rigid objects that can occlude major portions of the camera view. For example, in the task of mobile manipulation, the manipulated can be large and close to camera, therefore causing large occlusion. Previous approaches treat dynamic parts of a scene as outliers and are thus limited to a small amount of changes in the scene, or rely on prior information for all objects in the scene to enable robust camera tracking. Here, we propose to treat all dynamic parts as one rigid body and simultaneously segment and track both static and dynamic components.
We, therefore, enable simultaneous localisation and reconstruction of both the static background and rigid dynamic components in environments where dynamic objects cause large occlusion. We evaluate our approach on multiple challenging scenes with large dynamic occlusion. The evaluation demonstrates that our approach achieves better motion segmentation, localisation and mapping without requiring prior knowledge of the dynamic object's shape and appearance.
The first author is Ran Long, he is currently a 2nd year PhD student in the SLMC group from the University of Edinburgh and is supervised by Professor Sethu Vijayakumar FRSE. His research interest is estimating the trajecotries of multiple rigid bodies from RGB-D sequences using the understanding of robots’ actions, such as robot proprioception or kinematic.
The corresponding author of this paper is Professor Sethu Vijayakumar. Professor Vijayakumar is Professor of Robotics at the University of Edinburgh. He directs one of our International Collaboration Joint Project titled [Mobile Collaborative Robots: Addressing Real World Challenges] between the University of Edinburgh and AIRS. His research interest spans a broad interdisciplinary curriculum involving basic research in the fields of robotics, statistical machine learning, motor control, planning and optimization in autonomous systems and computational neuroscience.
Fulll text: https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=9380340
2. Task-Space Decomposed Motion Planning Framework for Multi-Robot Loco-Manipulation
This paper introduces a novel task-space decomposed motion planning framework for multi-robot simultaneous locomotion and manipulation. When several manipulators hold an object, closed-chain kinematic constraints are formed, and it will make the motion planning problems challenging by inducing lower-dimensional singularities. Unfortunately, the constrained manifold will be even more complicated when the manipulators are equipped with mobile bases. We address the problem by introducing a dual-resolution motion planning framework which utilizes a convex task region decomposition method, with each resolution tuned to efficient computation for their respective roles. Concretely, this dual-resolution approach enables a global planner to explore the low-dimensional decomposed task-space regions toward the goal, then a local planner computes a path in high-dimensional constrained configuration space. We demonstrate the proposed method in several simulations, where the robot team transports the object toward the goal in the obstacle-rich environments.
The first author of this paper is Xiaoyu Zhang, who is currently a research assistant at AIRS and he is a member of “Multi-Agent Collaborative Manipulation” of the international joint research project between AIRS and UoE. His research interest is robot motion planning and control.
The corresponding author of this paper is Lei Yan, who is currently a postdoc at UoE in UK and he is the strand leader of “Multi-Agent Collaborative Manipulation” of the international joint research project between AIRS and UoE. His research interests include impact-aware manipulation and decentralized planing and control for multi-robot system.
3. Decentralized Ability-Aware Adaptive Control for Multi-Robot Collaborative Manipulation (RA-L)
Multi-robot collaboration is extremely challenging due to the different kinematic and dynamics capabilities of the robots, the limited communication between them, and the uncertainty of the system parameters. To address these challenges, we propose a Decentralized Ability-Aware Adaptive Control (DA3C) method, in which the force capability of each robot is maximized by exploiting its null-space motion, while the designed adaptive controller enables decentralized coordination according to the capability of each robot. Simulation results show the proposed method can achieve online adaptation and accurate trajectory tracking irrespective of the low-level controllers, and can be used for heterogeneous multi-robot systems.
The first author of this paper is Lei Yan, who is currently a postdoc at UoE in UK and he is the strand leader of “Multi-Agent Collaborative Manipulation” of the international joint research project between AIRS and UoE. His research interests include impact-aware manipulation and decentralized planing and control for multi-robot system.
The corresponding author of this paper is Professor Sethu Vijayakumar. Professor Vijayakumar is Professor of Robotics at the University of Edinburgh. He directs one of our International Collaboration Joint Project titled [Mobile Collaborative Robots: Addressing Real World Challenges] between the University of Edinburgh and AIRS. His research interest spans a broad interdisciplinary curriculum involving basic research in the fields of robotics, statistical machine learning, motor control, planning and optimization in autonomous systems and computational neuroscience.
Full text: https://ieeexplore.ieee.org/document/9357952
4. Versatile Locomotion by Integrating Ankle, Hip, Stepping, and Height Variation Strategies
Stable walking in real-world environments is a challenging task for humanoid robots, especially when considering the dynamic disturbances, e.g., caused by external perturbations that may be encountered during locomotion. In this paper, we propose an enhanced Nonlinear Model Predictive Control (NMPC) approach for robust and adaptable walking – we term it versatile locomotion, by limiting both the Center of Pressure (CoP) and Divergent Component of Motion (DCM) movements. Due to utilization of the Nonlinear Inverted Pendulum plus Flywheel model, the robot is endowed with the capabilities of CoP manipulation (if equipped with finite sized feet), step location adjustment, upper body rotation, and vertical height variation. Considering the feasibility constraints, especially the usage of relaxed CoP constraints, the NMPC scheme is established as a Quadratically Constrained Quadratic Programming problem, which is solved efficiently by Sequential Quadratic Programming with enhanced solvability. Simulation experiments demonstrate the effectiveness of our method to recruit optimal hybrid strategies in order to realize versatile locomotion, for the robot with finite-sized or point feet.
The first author of this paper is Jiatao Ding, who is currently an assistant research scientist at AIRS and he is the member of “Multi-contact motion planning” of the international joint research project between AIRS and UoE. His research interest is locomotion planning and control for humanoid robots.
The external supervisor is Professor Sethu Vijayakumar. Professor Vijayakumar is Professor of Robotics at the University of Edinburgh. He directs one of our International Collaboration Joint Project titled [Mobile Collaborative Robots: Addressing Real World Challenges] between the University of Edinburgh and AIRS. His research interest spans a broad interdisciplinary curriculum involving basic research in the fields of robotics, statistical machine learning, motor control, planning and optimization in autonomous systems and computational neuroscience.
* The authors of the mentioned papers contributed to this article