An integrated system for autonomous robotics manipulation

Bagnell, J. Andrew; Cavalcanti, Felipe Lira de Sá; Cui, Lei; Galluzzo, Thomas C; Hebert, Martial; Kazemi, Moslem; Klingensmith, Matthew; Libby, Jacqueline; Liu, Tian Yu; Pollard, Nancy S.; Pivtoraiko, Mihail; Valois, Jean-Sebastien; Zhu, Ranqi

doi:10.1109/iros.2012.6385888

Cited by 103 publications

(87 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Recent advances in motion planning, control, and perception have enabled robotic systems to perform complex manipulation tasks in real world domains [3], [8], [7], [31], [33]. These systems perform integrated task and motion planning (see e.g., [1], [6], [16], [40]) by using state machines or task graphs [4], [34] for high-level task specification and motion planning algorithms for realization of low-level subtasks.…”

Section: Related Workmentioning

confidence: 99%

Autonomous multilateral debridement with the Raven surgical robot

Kehoe

Kahn

Mahler

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

113

View full text Add to dashboard Cite

Abstract-Robotic surgical assistants (RSAs) enable surgeons to perform delicate and precise minimally invasive surgery. Currently these devices are primarily controlled by surgeons in a local tele-operation (master-slave) mode. Introducing autonomy of surgical sub-tasks has the potential to assist surgeons, reduce fatigue, and facilitate supervised autonomy for remote tele-surgery. This paper considers the sub-task of surgical debridement: removing dead or damaged tissue fragments to allow the remaining healthy tissue to heal. We present an implemented automated surgical debridement system that uses the Raven, an open-architecture surgical robot with two cabledriven 7 DOF arms. Our system combines stereo vision for 3D perception, trajopt, an optimization-based motion planner, and model predictive control (MPC). Experiments with autonomous sensing, grasping, and removal of over 100 fragments suggest that it is possible for an autonomous surgical robot to achieve robustness comparable to human levels for a surgically-relevant subtask, although for our current implementation, execution time is 2-3× slower than human levels, primarily due to replanning times for MPC. This paper provides three contributions: (i) introducing debridement as a surgically-relevant sub-task for robotics, (ii) designing and implementing an autonomous multilateral surgical debridement system that uses both arms of the Raven surgical robot, and (iii) providing experimental data that highlights the importance of accurate state estimation for future research.

show abstract

Section: Related Workmentioning

confidence: 99%

Autonomous multilateral debridement with the Raven surgical robot

Kehoe

Kahn

Mahler

et al. 2014

2014 IEEE International Conference on Robotics and Automation (ICRA)

113

View full text Add to dashboard Cite

show abstract

“…To evaluate our algorithm, we conducted dozens of experiments with a robotic manipulation system [1]. In our experiments, a variety of unknown (manmade and natural) objects were placed on a table in front of the robot (e.g., Fig.…”

Section: Resultsmentioning

confidence: 99%

“…If an a priori CAD model of the target object is available, edge detection or primal sketches can be used to find a match [18]. When multiple images of an object are available, they can be used as templates to find the closet match [1]. The most important limitation of methods that rely on a priori models is that in unstructured environments such as our homes and offices, those models are unlikely to be available for all objects.…”

Section: B Object Detectionmentioning

confidence: 99%

“…To overcome this uncertainties, we rely on a library of compliant controllers which maintain proper contact with the environment during the robot's motion by responding to the detected contact forces. The robot motion is planned using CHOMP [1] to minimize contact with the environment. Our compliant controllers are described in detail in [15].…”

Section: Action Selection and Compliant Interactionmentioning

confidence: 99%

See 1 more Smart Citation

Clearing a Pile of Unknown Objects using Interactive Perception

Katz¹,

Kazemi²,

Bagnell³

et al. 2012

Self Cite

View full text Add to dashboard Cite

Abstract-We address the problem of clearing a pile of unknown objects using an autonomous interactive perception approach. Our robot hypothesizes the boundaries of objects in a pile of unknown objects (object segmentation) and verifies its hypotheses (object detection) using deliberate interactions. To guarantee the safety of the robot and the environment, we use compliant motion primitives for poking and grasping. Every verified segmentation hypothesis can be used to parameterize a compliant controller for manipulation or grasping. The robot alternates between poking actions to verify its segmentation and grasping actions to remove objects from the pile. We demonstrate our method with a robotic manipulator. We evaluate our approach with real-world experiments of clearing cluttered scenes composed of unknown objects.

show abstract

“…Thus, our controllers must be robust to uncertainty in modeling and localization. Our system uses CHOMP [20] to plan a collision free trajectory to an action launch pose (i.e., robot hand pose) based on the COG and orientation of the facet. Then we execute a compliant controller which maintains proper contact with the environment by responding to the detected contact forces.…”

Section: Compliant Motion Primitivesmentioning

confidence: 99%

Perceiving, learning, and exploiting object affordances for autonomous pile manipulation

et al. 2014

Self Cite

View full text Add to dashboard Cite

Abstract-Autonomous manipulation in unstructured environments presents roboticists with three fundamental challenges: object segmentation, action selection, and motion generation. These challenges become more pronounced when unknown manmade or natural objects are cluttered together in a pile. We present an end-to-end approach to the problem of manipulating unknown objects in a pile, with the objective of removing all objects from the pile and placing them into a bin. Our robot perceives the environment with an RGB-D sensor, segments the pile into objects using non-parametric surface models, computes the affordances of each object, and selects the best affordance and its associated action to execute. Then, our robot instantiates the proper compliant motion primitive to safely execute the desired action. For efficient and reliable action selection, we developed a framework for supervised learning of manipulation expertise. We conducted dozens of trials and report on several hours of experiments involving more than 1500 interactions. The results show that our learning-based approach for pile manipulation outperforms a common sense heuristic as well as a random strategy, and is on par with human action selection.

show abstract

An integrated system for autonomous robotics manipulation

Cited by 103 publications

References 16 publications

Autonomous multilateral debridement with the Raven surgical robot

Autonomous multilateral debridement with the Raven surgical robot

Clearing a Pile of Unknown Objects using Interactive Perception

Perceiving, learning, and exploiting object affordances for autonomous pile manipulation

Contact Info

Product

Resources

About