A summary of team MIT's approach to the virtual robotics challenge

Abstract

The attached video describes the system developed by researchers from MIT for the Defense Advanced Research Projects Agency's (DARPA) Virtual Robotics Challenge (VRC), held in June 2013. The VRC was the first competition in the DARPA Robotics Challenge (DRC), a program that aims to "develop ground robotic capabilities to execute complex tasks in dangerous, degraded, human-engineered environments" [1]. The VRC required teams to guide a model of Boston Dynamics' humanoid robot, Atlas, through driving, walking, and manipulation tasks in simulation.Team MIT's approach centered around teleautomation, in which an operator provided high-level instructions to be carried out autonomously by the robot. The resulting system comprised a 3D user interface coupled with perception, planning, control, and networking modules. The system's perception and planning abilities were assisted by the human operator(s) as needed.Team MIT's user interface, the Viewer, provided the operator with a unified representation of all available information. A 3D rendering of the robot depicted its most recently estimated body state with respect to the surrounding environment, represented by point clouds and texture-mapped meshes as sensed by on-board LIDAR and fused over time.Inertial and kinematic measurements were combined to provide accurate estimates of the robot's body state. The pose of the robot's pelvis was estimated by freely propagating inertial acceleration and rotation rate measurements. Joint angle measurements were combined with the kinematic robot model to propagate special footstep representations in the local navigational frame. Discrepancies between inertial and kinematic estimates were used in a feedback process to correct inertial sensor and navigational state errors.To overcome the uplink restrictions of the VRC, Team MIT's networking module employed an informationtheoretic coding algorithm to compress plans prior to sending them to the robot. This encoder, based on the Goby Project [2], allowed for compression ratios of over 30:1.The planning and control infrastructure consisted of two modes: manipulation and walking. The operator initiated manipulation planning by requesting a grasp for a specified object. A grasp optimizer then suggested an appropriate grasp location for the indicated hand. The operator could then request manipulation plans to reach for, grasp, or move the object. Requests were transmitted to a whole-body planner that computed joint trajectories which could achieve the manipulation goal while satisfying stability constraints. Candidate plans were displayed in the Viewer as a sequence of ghosted renderings of the robot, through which the operator could "scrub." The operator could modify the plan before transmitting it to the robot for autonomous execution.The operator initiated walking planning by specifying a navigation goal that triggered the footstep planner to compute a set of safe footsteps given the current estimate of the terrain. These footsteps were displayed in the Viewer for adjustment as needed. ...

Feedback Control of an Exoskeleton for Paraplegics: Toward Robustly Stable, Hands-Free Dynamic Walking

“…In particular, low-level control strategies are either position-based [30]- [34] or torque / force-based [35]- [39], while a higher-level impedance or admittance controller is used to regulate human-device interaction forces. This is in stark contrast to the surge in control technology for highly dynamic bipedal locomotion [40]- [45], where tools are being developed that allow rapid design of gaits and model-based feedback controllers, that respect physical constraints of the system such as torque limits and joint speeds, while providing formal guarantees on stability, safety and robustness to uncertainties in the model and in the environment [46]- [50]. If the control and design methodologies underlying advanced locomotion strategies for bipedal robots can be successfully translated to powered prostheses and exoskeletons in a holistic and formal manner, the end result promises to be a new generation of wearable robotic devices that deliver the next level of stable, safe, and efficient mobility.…”

Realizing dynamic and efficient bipedal locomotion on the humanoid robot DURUS

“…The ZMP and capture point methods are robust and allow for a variety of walking behaviors; however, the resulting locomotion is typically slow and very energy consuming. More recently, there have been several optimization based controllers [10], [17], [8], [9], [24] proposed in response to the DARPA Robotics Challenge. However, these approaches have been applied mainly with ZMP and capture point heuristics coupled with constraints, offer no formal guarantees, and again lack efficiency.…”

Multi-modal and inertial sensor solutions for navigation-type factor graphs

“…Humanoids require both a high bandwidth vehicle state estimate, as well as a long term stable and accurate solution [54,223]. Existing state estimate solutions, including [5,24,55,199] estimate.…”

“…Top right shows the SPHERES/VERTIGO experiment aboard the International Space Station during early testing in 2013 of the visual relative object tracking and inertial navigation experiments along with directional, synchronized time-of-flight acoustic beacons for absolute ranging and reference [66,67]. Bottom left shows the Team MIT's BDi Atlas humanoid robot (later 2013) for the DARPA robotics challenge, using a kinematic and lidar aided inertial navigation system, with the intention of remote user manipulation of objects [54,223]. Bottom right shows the Woods Hole Oceanographic Sentry autonomous under water vehicle before deployment at Juan de Fuca ridge in 2014, using multiple inertial sensors and Doppler velocity log for navigation; as well as independent acoustic and optical localization of equipment deployed on the sea floor [85,189].…”