Mehmet Remzi Dogar

A Framework for Push-Grasping in Clutter

Humans use a remarkable set of strategies to manipulate objects in clutter. We pick up, push, slide, and sweep with our hands and arms to rearrange clutter surrounding our primary task. But our robots treat the world like the Tower of Hanoi — moving with pick-and-place actions and fearful to interact with it with anything but rigid grasps. This produces inefficient plans and is often inapplicable with heavy, large, or otherwise ungraspable objects. We introduce a framework for planning in clutter that uses a library of actions inspired by human strategies. The action library is derived analytically from the mechanics of pushing and is provably conservative. The framework reduces the problem to one of combinatorial search, and demonstrates planning times on the order of seconds. With the extra functionality, our planner succeeds where traditional grasp planners fail, and works under high uncertainty by utilizing the funneling effect of pushing. We demonstrate our results with experiments in simulation and on HERB, a robotic platform developed at the Personal Robotics Lab at Carnegie Mellon University.

Push-grasping with dexterous hands: Mechanics and a method

We add to a manipulators capabilities a new primitive motion which we term a push-grasp. While significant progress has been made in robotic grasping of objects and geometric path planning for manipulation, such work treats the world and the object being grasped as immovable, often declaring failure when simple motions of the object could produce success. We analyze the mechanics of push-grasping and present a quasi-static tool that can be used both for analysis and simulation. We utilize this analysis to derive a fast, feasible motion planning algorithm that produces stable pushgrasp plans for dexterous hands in the presence of object pose uncertainty and high clutter. We demonstrate our algorithm extensively in simulation and on HERB, a personal robotics platform developed at Intel Labs Pittsburgh.

Herb 2.0: Lessons Learned From Developing a Mobile Manipulator for the Home

We present the hardware design, software architecture, and core algorithms of Herb 2.0, a bimanual mobile manipulator developed at the Personal Robotics Lab at Carnegie Mellon University, Pittsburgh, PA. We have developed Herb 2.0 to perform useful tasks for and with people in human environments. We exploit two key paradigms in human environments: that they have structure that a robot can learn, adapt and exploit, and that they demand general-purpose capability in robotic systems. In this paper, we reveal some of the structure present in everyday environments that we have been able to harness for manipulation and interaction, comment on the particular challenges on working in human spaces, and describe some of the lessons we learned from extensively testing our integrated platform in kitchen and office environments.

Physics-Based Grasp Planning Through Clutter

We propose a planning method for grasping in cluttered environments, where the robot can make simultaneous contact with multiple objects, manipulating them in a deliberate and controlled fashion. This enables the robot to reach for and grasp the target while simultaneously contacting and moving aside obstacles in order to clear a desired path. We use a physicsbased analysis of pushing to compute the motion of each object in the scene in response to a set of possible robot motions. In order to make the problem computationally tractable, we enable multiple simultaneous robot-object interactions, which we pre-compute and cache, but avoid object-object interactions. Tests on large sets of simulated scenes show that our planner produces more successful grasps in more complex scenes than versions that avoid any interaction with surrounding clutter. Validation on a real robot shows that our grasp evaluation method accurately predicts the outcome of a grasp, and that our approach, in conjunction with state-of-the-art object recognition tools, is applicable in reallife scenes that are highly cluttered and constrained.

A Planning Framework for Non-Prehensile Manipulation under Clutter and Uncertainty

Robotic manipulation systems suffer from two main problems in unstructured human environments: uncertainty and clutter. We introduce a planning framework addressing these two issues. The framework plans rearrangement of clutter using non-prehensile actions, such as pushing. Pushing actions are also used to manipulate object pose uncertainty. The framework uses an action library that is derived analytically from the mechanics of pushing and is provably conservative. The framework reduces the problem to one of combinatorial search, and demonstrates planning times on the order of seconds. With the extra functionality, our planner succeeds where traditional grasp planners fail, and works under high uncertainty by utilizing the funneling effect of pushing. We demonstrate our results with experiments in simulation and on HERB, a robotic platform developed at the Personal Robotics Lab at Carnegie Mellon University.

Pose estimation for contact manipulation with manifold particle filters

We investigate the problem of estimating the state of an object during manipulation. Contact sensors provide valuable information about the object state during actions which involve persistent contact, e.g. pushing. However, contact sensing is very discriminative by nature, and therefore the set of object states that contact a sensor constitutes a lower-dimensional manifold in the state space of the object. This causes stochastic state estimation methods, such as particle filters, to perform poorly when contact sensors are used. We propose a new algorithm, the manifold particle filter, which uses dual particles directly sampled from the contact manifold to avoid this problem. The algorithm adapts to the probability of contact by dynamically changing the number of dual particles sampled from the manifold. We compare our algorithm to the conventional particle filter through extensive experiments and we show that our algorithm is both faster and better at estimating the state. Unlike the conventional particle filter, our algorithms performance improves with increasing sensor accuracy and the filters update rate. We implement the algorithm on a real robot using commercially available tactile sensors to track the pose of a pushed object.

Object search by manipulation

We investigate the problem of a robot searching for an object. This requires reasoning about both perception and manipulation: certain objects are moved because the target may be hidden behind them and others are moved because they block the manipulators access to other objects. We contribute a formulation of the object search by manipulation problem using visibility and accessibility relations between objects. We also propose a greedy algorithm and show that it is optimal under certain conditions. We propose a second algorithm which is optimal under all conditions. This algorithm takes advantage of the structure of the visibility and accessibility relations between objects to quickly generate optimal plans. Finally, we demonstrate an implementation of both algorithms on a real robot using a real object detection system.

Pregrasp Manipulation as Trajectory Optimization.

We explore the combined planning of pregrasp manipulation and transport tasks. We formulate this problem as a simultaneous optimization of pregrasp and transport trajectories to minimize overall cost. Next, we reduce this simultaneous optimization problem to an optimization of the transport trajectory with start-point costs and demonstrate how to use physically realistic planners to compute the cost of bringing the object to these start-points. We show how to solve this optimization problem by extending functional gradient-descent methods and demonstrate our planner on two bimanual manipulation platforms.