Dreamer wishes you happy holidays!
Arxiv preprint of our paper on non-periodic dynamic locomotion.
We are pleased to post the submission of our paper "A Framework for Planning and Controlling Non-Periodic Bipedal Locomotion" for journal publication. The draft paper describing the framework can be found by clicking below:
Presentations during Humanoids 2015 on Stabilizing Point Foot Biped Robots and Data Fusion
PhD student Donghyun Kim and Dr. Sentis present their experimental work on bipedal locomotion and sensing.
President Greg Fenves and Dreamer.
What an honor to have UT Austin's president and Dreamer celebrating innovation at this great university.
Texas Tribune Festival's Innovation Showcase.
A very fun day talking to attendants of the Texas Tribune Festival, discussing STEM at UT Austin, and showcasing our research on cloud to hardware funded by NASA and the Longhorn Innovation Fund for Technology.
Longhorn's Innovation Fund for Technology Cloud-Based Advanced Robotics Laboratory Presentation
The focus of CARL, the Cloud-Based Advanced Robotics Laboratory, is to conduct research with robots using web browsers on mobile devices. For that, we provide a number of visualization and control tools, but most importantly the ability to gather experimental data for research.
Undergraduate Students Control Humanoid Robot and Show hardware Creation
Bridget Owens uses the CARL web framework designed by our laboratory to conduct experiments using humanoid robots. CARL allows not only to control humanoid robots but also collect data for motion analysis. Former undergraduate student Travis Llado has created and advanced research platform. In this case, Rocky is used for studies in rough terrain manipulation and is funded by NASA Johnson Space Center.
Valkyrie at DARPA's Robotics Challenge June 2015
This video showcases locomotion and teleoperation capabilities during demo time at the DRC finals. Valkyrie is NASA's humanoid robot designed and built using actuator technologies from our lab.
Three Valkyries and an MRV, and 20 years of NASA JSC ER4 history (Courtesy of NASA JSC)
Congratulations to NASA JSC for this great accomplishment. I am very happy to see the Valkyrie humanoids flourishing. I am also very proud of my lab to have helped design and build the actuators for this robot.
History Channel's Appearance of The Human Center Robotics Lab
Our research and some futurology are showcased in History Channel's Ancient Aliens series.
Oral Presentation at Dynamic Walking
Is your summer vacation a little dull? Watch our recent talk to inspire your curiosity ;) PhD student Donghyun Kim and Dr. Sentis, present a clear explanation on whole-body control and simple motion planning to stabilize bipeds with point feet. This presentation was delivered as part of Dynamic Walking 2015 in Columbus, Ohio.
Hume Becomes the Biped Robot with the Smallest Point Feet to Dynamically Balance Unsupported
Using Phase Space Locomotion Planning and Whole-Body Operational Space Control, Hume becomes the point-foot biped robot with the smallest feet able to balance unsupported.
ControlIt! Open-Source Whole-Body Control Software Framework for Humanoid Robots
We are pleased to announce ControlIt!, a new open-source software framework for Whole-Body Operational Space Control. It is offered with an LGPL v2.1 open source license. Installation and usage instructions are available here: ControlIt! Website. The draft paper describing the software framework can be found clicking below:
PhD Students Gray Thomas and Steven Jorgensen receive NASA Fellowships
Our team receives the NASA JSC Ellite Team Award for contributions on the design of Valkyrie
On the photo below: Liang Fok, Gwen Johnson, Luis Sentis, Nick Paine
N Steps with Phase Space Planning and Whole-Body Operational Space Control
The stabilizing properties of phase space planning in combination with the compliant SEA-based robot are shown for a N step task. Improvements on low level controllers allow the system to achieve its highest performance to date. Next improvement will be to enhance pose estimation.
IHMC Gets Valkyrie to Walk and Perform One Leg Balance. Valkyrie was designed by NASA JSC in collaboration with our lab at UT Austin
The Valkyrie robot at IHMC taking some steps and doing one legged balance routine. The robot is designed and built by NASA JSC in collaboration with the University of Texas at Austin. Control algorithms by IHMC. Funding for IHMC and UT Austin provided through the NSF/NASA National Robotics Initiative.
Towards Attractor Based Dynamic Stepping
In this video we show improvements on phase-space dynamic walking based on using an absolute return frame and the addition of Coriolis/centrifugal effects. The description of the planner can be found on Arxiv Preprint
IHMC NASA JSC X1 Exoskeleton Powered with UT-SEA Ankles
The Human Centered Robotics laboratory at UT Austin has collaborated with IHMC and NASA to integrate the high performance UT-SEA actuator in the X1 Exoskeleton assistive exoskeleton. The high power to weight ratio of the UT-SEA actuator provides a practical lightweight solution for wearable exoskeletons while fulfilling the demands on delivering high torques needed for walking assistance and rehabilitation.
Full-Body Collision Detection and Reaction with Omnidirectional Mobile Platforms: A Step Towards Safe Human-Robot Interaction
Arxiv Preprint. In the video below, we develop estimation and control methods for quickly reacting to collisions between omnidirectional mobile platforms and their environment. To enable the full-body detection of external forces, we use torque sensors located in the robot’s drivetrain. Using model based techniques we estimate the location, direction, and magnitude of collision forces, and we develop an admittance controller that achieves a low effective mass in reaction to them. For experimental testing, we use a facility containing a calibrated collision dummy and our holonomic mobile platform.
Hume Biped Robot Performing Balance on Split Terrain and Undirected Walking
Arxiv Preprint. The first experiment, shows the Hume biped robot balancing on a high pitch split terrain with and without push disturbances. We implement a Whole-Body Operational Space Controller to compute joint torques consistent with a desired set of operational space accelerations, known contact constraints, and desired internal forces. The internal forces, during multi- contact, correspond to the linear subspace of joint torques that do not cause accelerations of the robot. For undirected walking, Hume continuously steps forward and backward to remain balance. To accomplish this capability, we feed foot trajectories from an algorithm called Continuous Time to Velocity Reversal Online Planner. The planner continuously calculates new trajectories for the feet in an online fashion to recover from disturbances.
Luis Sentis Interview on Catalan's Leading Channel TV3
View on YouTube to see English subtitles
NASA Valkyrie Mechatronic Development - UT Austin Contributions on Design and Embedded Controls
The Valkyrie humanoid robot was built at NASA Johnson Space Center with leadership from Nic Radford and Rob Ambrose. The Human Centered Robotics Lab at UT Austin provided expertise in the design of rotary series elastic actuators and inspiration for the design of the linear series elastic actuators based on the UT-SEA design of our student Nick Paine. UT Austin also provided expertise on developing robust force controllers of the series elastic actuators and thorough testing on torque tracking and joint position impedance control.
The Legend of the Drunken Robot
This research is sponsored by the US Office of Naval Research. Hume uses its series elastic actuated legs to remain balanced while walking. It achieves this capability by observing the center of mass position error relative to a reference path and re-planning at every step a new reference trajectory to minimize the error. Re-lying on online continous replanning allows the robot to recover from the collisions with the rail stoppers.
First Implementation of Whole-Body Compliant Control with Internal Force Optimization on Hume
This movie shows the first successful implementation of the whole-body compliant controller ( IEEE TRO 2010) on Hume using its series elastic actuators . During the single contact phase, the robot's hip height and Saggital position, its torso orientation, and the trajectory of the swinging foot are controlled. During the dual contact phase the hip height, torso orientation, and the internal tension between the feet are controlled, instead. In both cases we use floating base dynamic models with contact constraints.
A Closed-Form Solution for Selecting Maximum Critically Damped Actuator Impedance Parameters, in press for the Journal of Dynamic Systems, Measurement and Control
Click on the image for a link to the PDF
Snapshots of Dreamer in the Transformers 4: Age of Extinction movie with Nicola Peltz and Mark Wahlberg
We filmed in Elgin, Texas with Director Michael Bay and actors Nicola Peltz and Mark Wahlberg. There is no wonder why the movie became a mega hit ;)
Human-Centered Robotic Technologies for Semi-Autonomous Systems and Health Applications
This video, shows snapshots from several groups at the University of Texas at Austin developing Human-Centered Robotic Technologies. Assistant Professor Luis Sentis describes his work on semi-autonomous humanoid robots for The Office of Naval Research, NASA, and DARPA. Assistant Professor Ashish Deshpande describes his research on robots that attach to the human body for rehabilitation and health assistive applications. Associate Professor Jonathan Dingwell studies physical and sensory impairment using virtual reality and robotic techniques. Finally, Assistant Professor James Sulzer develops robotic technologies for stroke rehabilitation using neuro-feedback of brain activity acquired through MRI scans.
Fully Omnidirectional Compliance in Mobile Robots
In order to make unintentional physical interaction with robots safer for humans, we develop compliant control of an omnidirectional wheeled base using Drive-Torque sensor feedback. The movie below shows a fully holonomic mobile robot system which achieves compliant motion via sensor-based force control, improving over previous pseudo-omnidirectional mobile systems by being fully omnidirectional. It shows compliance and safe interaction in both the mobile system alone and as the base of a wheeled mobile manipulator style system.
Dreamer Prepares and Delivers Science Certificates to the Austin Jewish Academy
Hume Walks in Flat Terrain and Overcomes and Obstacle Using UT's Phase Space Planning Techniques
In this video, showing results from our research funded by the US Office of Naval Research. UT's Hume bipedal robot executes the trajectories given by a Phase Space Planner. A video of UT's Phase Space Planner is shown further below.Congratulations to our students Donghyun Kim, Ye Zhao, Gray Thomas and Alan Kwok for their success!
Empirical Phase Space Plan Modifications
UT's Phase Space Dynamic Locomotion Planner in Action
The video below shows a simulation of our Phase Space Planner in a very difficult terrain. Because the model has no ankle joints, the locomotion maneuver is highly dynamic.
Valkyrie Rehearsing at the DARPA Robotic Challenge Trials in Miami
NASA, the Human Centered Robotics Lab at UT Austin and Texas A&M made it to the DRC Trials. Here Valkyrie manipulates a valve while standing up. Valkyrie is a new bipedal robot that was designed and built from scratch in just 9 months. Although this year we did not have a lot of time to get the hardware and software finalized to fully compete, we are here in the competition for the endgame in 2014.
Videos of Valkyrie Using Whole-Body Compliant Control
In the first video, Valkyrie, aided by a new whole-body compliant control and planning architecture, turns an industrial valve while being assisted by a skilled operator. In the second video, Valkyrie undergoes a series of tests to coordinate her upper and lower body.
Hume's Performance Results with Force Control SEA actuators
A new contol architecture that utilizes effectively the force controlled Series Elastic Actuators of Hume is put to use for precision motion tracking under gravity disturbances
Whole-Body Compliant Mobility in Sloped Terrains, Accepted to Springer's Autonomous Robots
"Implementation and stability analysis of prioritized whole-body compliant controllers on a wheeled humanoid robot in uneven terrains", Springer's Autonomous Robots, Vol. 35, Nu. 4, pp. 301-319, August 2013.
Click on the image below for a link to the PDF
Paper on Mobility in Rough and Cluttered Environments gets accepted to European Conference on Mobile Robotics
Bumping into walls
Bumping into humans!
UT Series Elastic Actuator, Accepted to IEEE/ASME Transactions on Mechatronics
"Design and Control Considerations for High Performance Series Elastic Actuators", IEEE/ASME Transactions on Mechatronics, In Press
Link to the video
Click on the image below for a link to the PDF
Dreamer Receives a New Arm
Dreamer receives a new 7 Degree of Freedom, Series Elastic Arm manufactured by Meka. A new gripper is being designed to allow dual hand manipulation.
Gyroscopic Telemanipulation of a Blindfolded Human
Trikey Compliant Mobile Base 2012 Completed
Talk at Dynamic Walking 2012
Dr. Sentis gives a talk at Dynamic Walking 2012 on Rough Terrain Locomotion.
Slides from Robotics Science and Systemspdf
UT-SEA: Compact, High Power, Light-Weight, Series Elastic Actuator
UT-SEA is a compact, light-weight, high-power actuator designed to enable energetic and high speed locomotion in electrically actuated legged systems. It uses a ballscrew as the primary speed reduction mechanism resulting in very high operating efficiency. The actuator is mounted on a set of springs which allows it to tolerate impact loads, store energy, and control force with high fidelity.
ONR, funds our project "HAWK: Hyper-Agile WalKing Controller for Bipedal Robots Aboard Navy Vessels"
Rough Terrain Manipulation Using the Dreamer/Meka Mobile Humanoid
DARPA Robotics Challenge
The New Hume Bipedal Robot
The new Dreamer/Meka compliant humanoid robot
Series Elastic Actuator of Hume
Details of the new knee actuator of the bipedal robot Hume.
Illustrations of the Hume Biped for Fast Locomotion in Irregular Terrains
UT Austin's biped robot for fast rough terrain locomotion. The Hume biped will be capable of maneuvering on terrains with height variations between 0-40 [cm] at speeds above 1 [m/s]. It uses SEA actuators with joint velocities above 10 [rad/s] and joint torques above 100 [Nm]. Its overall weight is 15 [Kg] and its overall height is 1.6 [m] thus resembling a mid size person.
Motion Planning of Extreme Locomotion Maneuvers, Humanoids 2011
The HCRL on YNN TV Channel at Barnes & Noble
Kids in North Austin had a sneak peek at the future Saturday. Saturday, the Barnes & Noble story in the Arboretum hosted Dreamer, an artificially intelligent humanoid robot. Dreamer's brain was programmed by the scientists at UT's Human Centered Robotics Lab. One of those scientists, Dr. Luis Sentis, was on hand to demonstrate what the robot can do. His work deals mostly with force augmentation, which looks into how robots can help to augment the movements of humans. The event had future roboticists in mind. Money from coffee and books sales will go to the Anderson High School Robotics Program.
Stability Analysis to Plan Dynamic Locomotion in Very Rough Terrain, IROS 2011, ISRR 2011
Master's Project: Tricky, Force Controlled Holonomic Base
Master's students, Somudro Gupta (demonstrator) and Pius Wong (video) show their work on design and control of our new holonomic base Tricky. Tricky employs omni wheels set in a triangular configuration to achieve omni-directional force control. It uses three Maxon motors rated at 250W with 3 stage planetary gears and 60 gear ratio providing 18Nm of torque per wheel. To control the torques, we have developed a new amplifier board capable of doing both current and load cell feedback. The board uses a Freescale 8-bit MC9S08MP16 microcontroller to achieve servo rates of 4KHz. The movie shows force interactions between the base and a user, based on servoing torque feedback.
Spotlight on the multi-contact/grasp matrix for the control of compliant legged robots
The HCRL Lab hosts Marc Raibert
We were very happy to hosty Marc. The visit took place on Wednesday Feb 16, 2011.
Dreamer says hello to Willow Garage
These sketches present our current progress in compliant control of humanoid robots at Willow Garage. The idea is to combine torque-based compliant behaviors for Cartesian and joint space tasks. This approach enables to respond quickly to contact, be safe and use effectively the dynamics of the mechanism. The focus of this research is more on the skill than on the single low level control process. We provide infrastructure to bridge the gap between the skill developer (who cares about the mathematics of movement and robot dynamics) and the skill user (who cares about motion / high level planning and perception).
The DREAMER Meka-HCRL Sociable Head Arrives to the Lab
Experiments on prioritized compliant control
This video shows various experiments of the control of UT Austin's humanoid Meka robot. We demonstrate prioritized torque control strategies, addressing hand position tasks and dynamically compensated posture optimization. In particular, the main contribution of the experiments is the ability to optimize posture performance by dynamically compensating the postural mass matrix with the task's null space matrix.
Compliant Control Experiments on the Meka Robot
Collaborative implementation of compliant control with Stanford Univ. and Willow Garage. Three experiments are shown: (a) gravity effort compensation to validate the robot's dynamic and kinematic model, (b) dynamically weighted posture control to demonstrate the validity of the mass/inertia matrix, and (c) operational space compliant control in the vertical and Sagittal directions to demostrate the ability to respond to the environment using the tool.
Testing of Fluidic Muscles
A series of experiments to validate the capabilities of a high force compliant fluidic actuator in terms of tracking bandwidth, stiffness regulation, gravity compensation, and torque control.