The results show that the robot was able to transition between the different motion primitives required for navigating through the complex environment and that such motions are realisable for hexapods. This paper reports some preliminary work on learning on a physical robot. In particular, we report on an experiment to learn how to strike a ball to hit a target on the ground.
About this book
We compare learning based just on previous trials with the robot with learning based on those trials plus additional data learnt using a generative adversarial network GAN. We find that the additional data generated by the GAN improves the performance of the robot. Recent demographics indicate that we have a growing population of older adults with increasingly complex care-related needs, and a shrinking care workforce with limited resources to support them. In this paper, we propose a robot-based coaching system which encourages collaboration with the user to collect person-specific exercise-related movement data.
The aim is to personalise the experience of exercise sessions and provide directed feedback to the user to help improve their performance. The way each individual user is likely to perform specific movements will be based on their personal ability and range of motion, and it is important for a coaching system to recognise the movements and map the feedback to the user accordingly.
We show how a machine learning technique, a Nearest Neighbour classifier enhanced with a confidence metric, is used to build a personalised database of 3D skeletal tracking data. This approach, combined with collaborative Human-Robot Interaction to collect the data, could be used for robust and adaptable exercise performance tracking by a collaborative robot coach, using the information to provide personalised feedback.
Though these systems operate close to real time, there is lacking a study of the ways to achieve real-time performance by trading off between semantic model accuracy and computational requirements.
Probabilistic planning is very useful for handling uncertainty in planning tasks to be carried out by robots. This systems paper presents a standardized integration of probabilistic planners into ROSPlan that allows for reasoning with non-deterministic effects and is agnostic to the probabilistic planner used. We instantiate the framework in a system for the case of a mobile robot performing tasks indoors, where probabilistic plans are generated and executed by the PROST planner. We evaluate the effectiveness of the proposed approach in a real-world robotic scenario.
Aerial coverage path planning is a type of path planning where the sensor footprint covers all accessible parts of the area of interest. This type of path planning finds application in precision agriculture, precision forestry and service robots.
- Robotic Systems.
- Oil Worker.
- An Autonomous Robotic System for Mapping Abandoned Mines?
- Food for the gods : new light on the ancient incense trade.
- God and the Victim: Traumatic Intrusions on Grace and Freedom (Aar Academy Series).
- Brickwork and paving : for house and garden!
Limited endurance of micro aerial vehicles has limited their operations to small areas coverable in a single flight. New application domains like geological survey cover vast areas exceeding endurances of most modern aerial platforms and the available path planners do not address coverage of such areas. This paper presents an approach for generating coverage paths for large-scale aerial mapping.
The planner applies voronoi partitioning to decompose large areas into manageable cells. Then generates boustrophedon paths to cover each cell. The proposed planner is incorporated into Mission Planner. Software in the loop simulation results have ascertained the feasibility and completeness of the generated paths, even with multiple micro aerial platforms. Collective motion is one of the most fascinating phenomena observed in nature. In the last decade, it aroused so much attention in physics, control and robotics fields.
In particular, many studies have been done in swarm robotics related to collective motion, also called flocking. In most of these studies, robots use orientation and proximity of their neighbors to achieve collective motion. In such an approach, one of the biggest problems is to measure orientation information using on-board sensors. In most of the studies, this information is either simulated or implemented using communication.
In this paper, we implemented a fully autonomous coordinated motion without alignment using very simple Mona robots. We modified the method and added the capability to enable the swarm to move toward a desired direction and rotate about an arbitrary point. We tested our approach in different settings using Matlab and Webots. Despite the great progress in quadrupedal robotics during the last decade, selecting good contacts footholds in highly uneven and cluttered environments still remains an open challenge.
This paper builds upon a state-of-the-art approach, already successfully used for humanoid robots, and applies it to our robotic platform; the quadruped robot ANYmal. The proposed algorithm decouples the problem into two subproblems: first a guide trajectory for the robot is generated, then contacts are created along this trajectory. Both subproblems rely on approximations and heuristics that need to be tuned.
The main contribution of this work is to explain how this algorithm has been retuned to work with ANYmal and to show the relevance of the approach with a variety of tests in realistic dynamic simulations. This paper addresses multi-robot multi-goal motion planning with temporal and resources constraints. It solves the vehicle routing problem for mobile robots that operate according to their system dynamics, and which have to visit a number of waypoints scattered in a two-dimensional map environment with obstacles, while satisfying time window and capacity constraints.
Macro actions enable the vehicles to run in real-time with best actions being distributed to the individual controllers. We analyze how the simulation is affected by varying parameters such as the number of vehicles. Musical instrument education has typically faced challenges in providing students with a cost-efficient and long-term solution for personalised tutoring.
To address these challenges, we propose a musical instrument tutor robot for students learning the recorder, called instruMentor. Equipped with robotic hands and a multimodal interface, the robot interacts with users by playing the recorder and demonstrating in real-time the proper handling of the instrument. A pilot study was conducted to investigate the effectiveness of a robot tutor for instrument learning.
Experimental results suggest that instruMentor is successful at teaching the recorder and is positively appreciated by users, showing promise for the future coupling of music tutoring and social robots. In this paper we describe how a generic interoperability telerobotics protocol can be applied for master-slave robotic systems operating in position-position, position-speed and hybrid control modes.
The interoperability protocol allows robust and efficient data exchange for teleoperation systems, however it was not shown how it can fit switching position and rate control modes.
Here we propose the general framework of hybrid position and rate control modes with interoperability protocol. In this paper we present a fully autonomous and intrinsically motivated robot usable for HRI experiments. We argue that an intrinsically motivated approach based on the Predictive Information formalism, like the one presented here, could provide us with a pathway towards autonomous robot behaviour generation, that is capable of producing behaviour interesting enough for sustaining the interaction with humans and without the need for a human operator in the loop.
- Southwest Airlines (Corporations That Changed the World);
- Details of Grant!
- Towards Autonomous Robotic Systems;
- Home - Robotics and Autonomous Systems Group?
- Graduate Certificate in Intelligent Robotic Systems.
We present a possible reactive baseline behaviour for comparison for future research. Participants perceive the baseline and the adaptive, intrinsically motivated behaviour differently. In our exploratory study we see evidence that participants perceive an intrinsically motivated robot as less intelligent than the reactive baseline behaviour. We argue that is mostly due to the high adaptation rate chosen and the design of the environment.
However, we also see that the adaptive robot is perceived as more warm, a factor which carries more weight in interpersonal interaction than competence. We present the design of a one-degree-of-freedom ankle actuation platform for human-robot interaction. The platform is actuated with a DC motor through a capstan drive mechanism.
The results for platform dynamics identification including friction characterisation are presented.
Distributed Autonomous Robotic Systems 4 | Lynne Parker | Springer
Control experiments demonstrate that a linear regulator with gravity compensation can be used to control the inclination of the platform efficiently. Identifying the roles and the specific social behaviours that evoke human trust towards robots is key for user acceptance. Specially, while performing tasks in the real world, such as navigation or guidance, the predictability of robot motion and predictions of user intentions facilitate interaction.
We present a user study in which a humanoid-robot guided participants around a human populated environment, avoiding collisions while following a socially acceptable trajectory.
20th Towards Autonomous Robotic Systems Conference
We investigated which behaviours performed by a humanoid robot during a guidance task exhibited better social acceptance by people, and how robot behaviours influence their trust in a robot to safely complete a guiding task. We concluded that in general, people prefer and trust a robot that exhibits social behaviours such as talking and maintaining an appropriate safe distance from obstacles. The development of autonomous robots for agriculture depends on a successful approach to recognize user needs as well as datasets reflecting the characteristics of the domain.
Available datasets for 3D Action Recognition generally feature controlled lighting and framing while recording subjects from the front. They mostly reflect good recording conditions and therefore fail to account for the highly variable conditions the robot would have to work with in the field, e.
Existing work on Intention Recognition mostly labels plans or actions as intentions, but neither of those fully capture the extend of human intent. In this work, we argue for a holistic view on human Intention Recognition and propose a set of recording conditions, gestures and behaviors that better reflect the environment and conditions an agricultural robot might find itself in. We demonstrate the utility of the dataset by means of evaluating two human detection methods: bounding boxes and skeleton extraction.
With the rise of Virtual Reality VR applications it is interesting to see how immersion can be improved, especially by providing haptic feedback on the user hands, using affordable technologies. Indeed, while several commercial products exist that can be used as input devices i. We describe here the design and realization of an affordable data glove to provide vibrotactile feedback to human users using small vibrating motors, and we report preliminary user studies to prove its effectiveness; interestingly, combined with a commercially available optical tracker i. Leap Motion to be used as input device, the data glove can be used in a wide range of Virtual Reality and Telerobotics applications.
Demcon Robotic Systems has knowledge of artificial intelligence AI and vision such as stereo cameras and has invested in SLAM expertise, simultaneous localisation and mapping. With SLAM an autonomous system such as a mobile robot can formulate a map of an unknown environment and use this map to navigate. In the control software, Demcon provides the autonomous robot with rules so that it can respond to unexpected situations.
Demcon has extensive experience with simulations and these help in formulating these rules in advance. For the final industrial implementation, Demcon takes care of the total programming in Python and C. This guarantees control software reliability and maintainability.
Autonomous Robotic Manipulation (ARM) (Archived)
The development of robotic systems at Demcon is not only software driven. As these indoor techniques continue to develop, vacuuming robots will gain the ability to clean a specific user-specified room or a whole floor. Security robots will be able to cooperatively surround intruders and cut off exits. These advances also bring concomitant protections: robots' internal maps typically permit "forbidden areas" to be defined to prevent robots from autonomously entering certain regions. Outdoor autonomy is most easily achieved in the air, since obstacles are rare. Cruise missiles are rather dangerous highly autonomous robots.
Pilotless drone aircraft are increasingly used for reconnaissance. Some of these unmanned aerial vehicles UAVs are capable of flying their entire mission without any human interaction at all except possibly for the landing where a person intervenes using radio remote control. Some drones are capable of safe, automatic landings, however. An autonomous ship was announced in —the Autonomous spaceport drone ship —and is scheduled to make its first operational test in December There are several open problems in autonomous robotics which are special to the field rather than being a part of the general pursuit of AI.
According to George A.