A humanoid robot standing up through learning from demonstration using a multimodal reward function

2013 ◽  
Author(s):  
Miguel Gonzalez-Fierro ◽  
Carlos Balaguer ◽  
Nicola Swann ◽  
Thrishantha Nanayakkara
Keyword(s):  
Humanoid Robot ◽  
Learning From Demonstration ◽  
Reward Function ◽  
Standing Up

Application of Generalized Function Set in the Lying States Classification of a Humanoid Robot

2013 ◽  
Vol 694-697 ◽  
pp. 1742-1746
Author(s):  
Kai Cheng Qi ◽  
Wei Liu ◽  
Peng Shang ◽  
Jian Jun Zhang ◽  
Feng Gao ◽  
...  
Keyword(s):  
Motion Planning ◽  
Supine Position ◽  
Generalize Function ◽  
Humanoid Robot ◽  
Generalized Function ◽  
State Classification ◽  
Equal Importance ◽  
Standing Up ◽  
End Effectors

Standing up from a supine position or sitting down from standing is an important and simple human activity of day life. It is of equal importance for a humanoid robot, but it is not simple work to be completed for the robot. This paper presents the concept of generalized function set, and researches on the characteristics of lying state using the generalize function (GF) set, and gets the interested end effectors (EEs), which is instructional in the next detailed motion planning. Then the work presents the lying state classification of the humanoid robot SJTU-HR1.

Analyzing and Reducing Energy Usage in a Humanoid Robot During Standing Up and Sitting Down Tasks

2016 ◽  
Vol 13 (04) ◽  
pp. 1650014 ◽  
Author(s):  
Ercan Elibol ◽  
Juan Calderon ◽  
Martin Llofriu ◽  
Wilfrido Moreno ◽  
Alfredo Weitzenfeld
Keyword(s):  
Humanoid Robot ◽  
Center Of Pressure ◽  
Center Of Mass ◽  
Electrical Power ◽  
Joint Torque ◽  
Q Learning ◽  
Current Usage ◽  
Standing Up ◽  
Joint Velocity ◽  
Joint Acceleration

The aim of this paper is to reduce the energy consumption of a humanoid by analyzing electrical power as input to the robot and mechanical power as output. The analysis considers motor dynamics during standing up and sitting down tasks. The motion tasks of the humanoid are described in terms of joint position, joint velocity, joint acceleration, joint torque, center of mass (CoM) and center of pressure (CoP). To reduce the complexity of the robot analysis, the humanoid is modeled as a planar robot with four links and three joints. The humanoid robot learns to reduce the overall motion torque by applying Q-Learning in a simulated model. The resulting motions are evaluated on a physical NAO humanoid robot during standing up and sitting down tasks and then contrasted to a pre-programmed task in the NAO. The stand up and sit down motions are analyzed for individual joint current usage, power demand, torque, angular velocity, acceleration, CoM and CoP locations. The overall result is improved energy efficiency between 25–30% when compared to the pre-programmed NAO stand up and sit down motion task.

scholarly journals “Hit the Robot on the Head With This Mallet” – Making a Case for Including More Open Questions in HRI Research

2021 ◽  
Vol 8 ◽  
Author(s):  
Katie A. Riddoch ◽  
Emily. S. Cross
Keyword(s):  
Recent Experiment ◽  
Humanoid Robot ◽  
Structured Interview ◽  
Task Instruction ◽  
Social Agents ◽  
Open Questions ◽  
Standing Up ◽  
Research Questions ◽  
New Research ◽  
Do So

Researchers continue to devise creative ways to explore the extent to which people perceive robots as social agents, as opposed to objects. One such approach involves asking participants to inflict ‘harm’ on a robot. Researchers are interested in the length of time between the experimenter issuing the instruction and the participant complying, and propose that relatively long periods of hesitation might reflect empathy for the robot, and perhaps even attribution of human-like qualities, such as agency and sentience. In a recent experiment, we adapted the so-called ‘hesitance to hit’ paradigm, in which participants were instructed to hit a humanoid robot on the head with a mallet. After standing up to do so (signaling intent to hit the robot), participants were stopped, and then took part in a semi-structured interview to probe their thoughts and feelings during the period of hesitation. Thematic analysis of the responses indicate that hesitation not only reflects perceived socialness, but also other factors including (but not limited to) concerns about cost, mallet disbelief, processing of the task instruction, and the influence of authority. The open-ended, free responses participants provided also offer rich insights into individual differences with regards to anthropomorphism, perceived power imbalances, and feelings of connection toward the robot. In addition to aiding understanding of this measurement technique and related topics regarding socialness attribution to robots, we argue that greater use of open questions can lead to exciting new research questions and interdisciplinary collaborations in the domain of social robotics.

scholarly journals Technique of Standing Up From Prone Position of a Soccer Robot

2018 ◽  
Vol 6 (1) ◽  
pp. 124-136 ◽  
Author(s):  
Nur Khamdi ◽  
Mochamad Susantok ◽  
Antony Darmawan
Keyword(s):  
Prone Position ◽  
Degrees Of Freedom ◽  
Humanoid Robot ◽  
Humanoid Robots ◽  
Soccer Robot ◽  
Robot Soccer ◽  
The Real ◽  
Limited Movement ◽  
Standing Up ◽  
Real Robot

One of the humanoid robots being developed in the field of sports is a soccer robot. A soccer robot is a humanoid robot that can perform activities such as playing football. And a variety method fall down of robot soccer such: falling down toward the front direction, side direction, and rear direction. This paper describes the most stands up methods of a soccer robot from its prone position. The proposed method requires only limited movement with degrees of freedom. The movement standing-up of soccer robot has been implemented on the real robot. Tests we performed showed that reliable standing-up from prone position is possible after a fall and such recovery procedures greatly improve the overall robustness of a Soccer Robot.

scholarly journals Full-Body Postural Control of a Humanoid Robot with Both Imitation Learning and Skill Innovation

2014 ◽  
Vol 11 (02) ◽  
pp. 1450012 ◽  
Author(s):  
Miguel González-Fierro ◽  
Carlos Balaguer ◽  
Nicola Swann ◽  
Thrishantha Nanayakkara
Keyword(s):  
Transition Probabilities ◽  
Temporal Structure ◽  
Kinematic Chain ◽  
Joint Torques ◽  
Motion Data ◽  
Reward Function ◽  
Standing Up ◽  
The Difference ◽  
Human Participants ◽  
The Stability

In this paper, we present a novel methodology to obtain imitative and innovative postural movements in a humanoid based on human demonstrations in a different kinematic scale. We collected motion data from a group of human participants standing up from a chair. Modeling the human as an actuated 3-link kinematic chain, and by defining a multi-objective reward function of zero moment point and joint torques to represent the stability and effort, we computed reward profiles for each demonstration. Since individual reward profiles show variability across demonstrating trials, the underlying state transition probabilities were modeled using a Markov chain. Based on the argument that the reward profiles of the robot should show the same temporal structure of those of the human, we used differential evolution to compute a trajectory that fits all humanoid constraints and minimizes the difference between the robot reward profile and the predicted profile if the robot imitates the human. Therefore, robotic imitation involves developing a policy that results in a temporal reward structure, matching that of a group of human demonstrators across an array of demonstrations. Skill innovation was achieved by optimizing a signed reward error after imitation was achieved. Experimental results using the humanoid HOAP-3 are shown.

Sign in / Sign up

Export Citation Format

Share Document