Robotics & Autonomous Systems
A*STAR I²R develops state-of-the-art service robot technology that would help to boost workforce productivity amidst Singapore’s aging population and the shortage of workers undertaking dangerous, dirty and dull jobs.
We imbue service robots with artificial intelligence, empowering them to operate in dynamic and unstructured environments, as well as to assist and collaborate with humans.
As robots are complex systems, we work closely with the wide range of expertise within the Institute and across the whole of A*STAR to realise unique prototypes with mid-to-high Technology Readiness Level (TRL) that our partners and the industries need.
Some of the success stories include the successful development of Autonomous Vehicle (AV), shelf scanning robots and patrolling robots, leading to spin-off such as MooVita Pte Ltd, Senserbot Pte Ltd and BotMind Pte Ltd.
Our core capabilities include Mobility, Perception, Manipulation and Human-Robot & Multiple-Robot Collaboration.
Robust Robot Mobility
The mobility group focuses on providing robust localization and intelligent navigation for robots to operate in human environment and in the presence of people. This is to enable robots to assist human effectively The outcome of the research will allow robots to be deployed safely in the midst of crowd and in unknown places with minimal human assistance, operating continuously 24x7 and even under heavy rain. Moreover, the robots will also have the intelligence to respond sensibly to any unplanned situations such as during emergencies, and to recover itself after an unforeseen disruption.
Active areas of research include fast online SLAM, 3D localization with large map management, safe navigation in crowded places, autonomous exploration in unmapped area, legged and hybrid locomotion, navigation in heavy rain and integrated traversability estimation and path planning.
We have also been actively collaborating with government agencies and industry partners to develop solutions in areas such as security, healthcare, inspection, and logistics. For example, the security robot developed in collaboration with HTX of MHA won the “Best Drones and Robotics Project” in the International GovInsider Innovation Awards 2018.
Active areas of research include fast online SLAM, 3D localization with large map management, safe navigation in crowded places, autonomous exploration in unmapped area, legged and hybrid locomotion, navigation in heavy rain and integrated traversability estimation and path planning.
We have also been actively collaborating with government agencies and industry partners to develop solutions in areas such as security, healthcare, inspection, and logistics. For example, the security robot developed in collaboration with HTX of MHA won the “Best Drones and Robotics Project” in the International GovInsider Innovation Awards 2018.
Multimodal Perception
Robotics perception is the module that endows a robotic system with the ability to understand and reason about its surrounding environment. This involves multimodal sensory data processing, environment modelling, and machine learning which are the key areas for the perception group. Depending on application requirements, we work with different sensing modalities and closely with the other groups to meet various goals such as robot localization, obstacles avoidance, object aware path planning, safety, and human robot interaction.
Active areas of research include optimal multimodal sensor fusion algorithm for a suite of commonly used sensors such as 2D/3D lidar, RGBD cameras, sonar array as well as new sensor modalities such as tactile elements and mm-wave radar for object detection, obstacle detection and environment understanding. Other active research topics include continuous perception under different lighting and weather conditions, robust object detection and affordance analysis, interactive perception and combining perception with task learning.
As robotic perception forms a close-loop tie with navigation and/or manipulation, we work closely to deploy our solution for various application domains including in hospitals, immigration check-points, perimeter and premise patrolling, infrastructure and aircraft inspection.
Active areas of research include optimal multimodal sensor fusion algorithm for a suite of commonly used sensors such as 2D/3D lidar, RGBD cameras, sonar array as well as new sensor modalities such as tactile elements and mm-wave radar for object detection, obstacle detection and environment understanding. Other active research topics include continuous perception under different lighting and weather conditions, robust object detection and affordance analysis, interactive perception and combining perception with task learning.
As robotic perception forms a close-loop tie with navigation and/or manipulation, we work closely to deploy our solution for various application domains including in hospitals, immigration check-points, perimeter and premise patrolling, infrastructure and aircraft inspection.
Dexterous Manipulation
The manipulation group performs research in autonomous and semi-autonomous robotic manipulation for service robots, and develops solutions, in tandem with perception and mobility groups, for real world applications.
Integrated with online perception, our manipulator systems are aware of environmental features and constraints, and are able to learn/plan the best actions and motions to perform manipulation tasks in uncertain/unstructured or human environments. Combining with locomotion (wheel/legged) enables our manipulator systems to have extended workspace, manipulability, and flexibility.
Active areas of research include tactile-based dexterous manipulation, loco-manipulation motion planning, task planning, manipulation learning, and human-robot shared autonomy. We focus on learning and planning based approaches to find (near-) optimal solutions to real world manipulation problems and enable more intelligent manipulation cognition and behaviors. Furthermore, we apply safe and intuitive human-in-the loop control to provide flexible and easy-to-use semi-autonomous operations in complex and challenging scenarios.
Applications (being) developed include indoor farming, aircraft inspection, robot-assisted immigration clearance, and humanitarian assistance and disaster relief (HADR), among others.
Integrated with online perception, our manipulator systems are aware of environmental features and constraints, and are able to learn/plan the best actions and motions to perform manipulation tasks in uncertain/unstructured or human environments. Combining with locomotion (wheel/legged) enables our manipulator systems to have extended workspace, manipulability, and flexibility.
Active areas of research include tactile-based dexterous manipulation, loco-manipulation motion planning, task planning, manipulation learning, and human-robot shared autonomy. We focus on learning and planning based approaches to find (near-) optimal solutions to real world manipulation problems and enable more intelligent manipulation cognition and behaviors. Furthermore, we apply safe and intuitive human-in-the loop control to provide flexible and easy-to-use semi-autonomous operations in complex and challenging scenarios.
Applications (being) developed include indoor farming, aircraft inspection, robot-assisted immigration clearance, and humanitarian assistance and disaster relief (HADR), among others.
Human-Robot & Multi-Robot Collaboration
As robotics technologies mature, robots are expected to work in a team and collaborating with other people, not only in a factory setup as a cobot but also increasing in our living spaces.
Focusing on the use of learning techniques, multiple sensory and interaction modalities, we seek to investigate on:
• Methods for safe interactions
• Methods for compliant and collaborative interactions
• Methods for coordinated actions to improve the quality of task completion
In order to develop capabilities and application for:
• Co-working and buddy robots for the professional industry
• Assistive robots to augment human potentials
• Care robots to improve quality of life
Focusing on the use of learning techniques, multiple sensory and interaction modalities, we seek to investigate on:
• Methods for safe interactions
• Methods for compliant and collaborative interactions
• Methods for coordinated actions to improve the quality of task completion
In order to develop capabilities and application for:
• Co-working and buddy robots for the professional industry
• Assistive robots to augment human potentials
• Care robots to improve quality of life
System Integration
To solve national priorities and deliver values to our research collaborators, we devote significant effort in performing rigorous system integration, combining our developed robotics component technologies with a suitable robot hardware to ensure that the resultant robot is able to meet the requirements for deployment. We collaborate closely with government agencies and companies to ensure what we developed are use-inspired. With the former, we co-innovate with them to address the challenges faced and then transfer the technology to companies in Singapore. With companies, we play various roles, from providing dedicated technology needed to enhance the companies’ products to developing complete prototypes as well as technology licensing.
Some of our developed robots include:
Some of our developed robots include:
A*STAR celebrates International Women's Day
From groundbreaking discoveries to cutting-edge research, our researchers are empowering the next generation of female science, technology, engineering and mathematics (STEM) leaders.