Martin Levihn

Hierarchical Decision Theoretic Planning for Navigation Among Movable Obstacles

In this paper we present the first decision theoretic planner for the problem of Navigation Among Movable Obstacles (NAMO). While efficient planners for NAMO exist, they are challenging to implement in practice due to the inherent uncertainty in both perception and control of real robots. Generalizing existing NAMO planners to nondeterministic domains is particularly difficult due to the sensitivity of MDP methods to task dimensionality. Our work addresses this challenge by combining ideas from Hierarchical Reinforcement Learning with Monte Carlo Tree Search, and results in an algorithm that can be used for fast online planning in uncertain environments. We evaluate our algorithm in simulation, and provide a theoretical argument for our results which suggest linear time complexity in the number of obstacles for typical environments.

Navigation Among Movable Obstacles in unknown environments

This paper explores the Navigation Among Movable Obstacles (NAMO) problem in an unknown environment. We consider the realistic scenario in which the robot has to navigate to a goal position in an unknown environment consisting of static and movable objects. The robot may move objects if the goal can not be reached otherwise or if moving the object may significantly shorten the path to the goal. We consider real situations in which the robot only has limited sensing information and where the action selection can therefore only be based on partial knowledge learned from the environment at that point. This paper introduces an algorithm that significantly reduces the necessary calculations to accomplish this task compared to a direct approach. We present an efficient implementation for the case of planar, axis-aligned environments and report experimental results on challenging scenarios with more than 50 objects.

Foresight and reconsideration in hierarchical planning and execution

We present a hierarchical planning and execution architecture that maintains the computational efficiency of hierarchical decomposition while improving optimality. It provides mechanisms for monitoring the belief state during execution and performing selective replanning to repair poor choices and take advantage of new opportunities. It also provides mechanisms for looking ahead into future plans to avoid making short-sighted choices. The effectiveness of this architecture is shown through comparative experiments in simulation and demonstrated on a real PR2 robot.

Planning with movable obstacles in continuous environments with uncertain dynamics

In this paper we present a decision theoretic planner for the problem of Navigation Among Movable Obstacles (NAMO) operating under conditions faced by real robotic systems. While planners for the NAMO domain exist, they typically assume a deterministic environment or rely on discretization of the configuration and action spaces, preventing their use in practice. In contrast, we propose a planner that operates in real-world conditions such as uncertainty about the parameters of workspace objects and continuous configuration and action (control) spaces. To achieve robust NAMO planning despite these conditions, we introduce a novel integration of Monte Carlo simulation with an abstract MDP construction. We present theoretical and empirical arguments for time complexity linear in the number of obstacles as well as a detailed implementation and examples from a dynamic simulation environment.

Using environment objects as tools: Unconventional door opening.

Robots should be able to utilize environment objects as tools. A critical challenge to accomplishing this task is the vast search space that arises when considering multiple interacting bodies. To manage this complexity, we introduce an approach which efficiently reasons by back-propagating physical constraints between useful combinations of objects. This approach allows us to exploit restrictions on relative object configurations to reduce the search space prior to committing to specific object choices. We present a simulated implementation of our approach applied to the problem of opening a jammed door. Our method allows a robot to efficiently choose between two strategies, leverage and impact, to achieve the desired result using various available objects.

Locally optimal navigation among movable obstacles in unknown environments

Mobile manipulators and humanoid robots should be able to utilize their manipulation capabilities to move obstacles out of their way. This concept is captured within the domain of Navigation Among Movable Obstacles (NAMO). While a variety of NAMO algorithms exists, they typically assume full world knowledge. In contrast, real robot systems only have limited sensor range and partial environment knowledge. In this work we present the first NAMO system for unknown environments capable of handling a large set of possible object motions and arbitrary object shapes while guaranteeing optimal decision making for the given knowledge. We demonstrate empirical results with up to 70 obstacles.

Learning non-holonomic object models for mobile manipulation

For a mobile manipulator to interact with large everyday objects, such as office tables, it is often important to have dynamic models of these objects. However, as it is infeasible to provide the robot with models for every possible object it may encounter, it is desirable that the robot can identify common object models autonomously. Existing methods for addressing this challenge are limited by being either purely kinematic, or inefficient due to a lack of physical structure. In this paper, we present a physics-based method for estimating the dynamics of common non-holonomic objects using a mobile manipulator, and demonstrate its efficiency compared to existing approaches.

Detecting partially occluded objects via segmentation and validation

This paper presents a novel algorithm: Verfied Partial Object Detector (VPOD) for accurate detection of partially occluded objects such as furniture in 3D point clouds. VPOD is implemented and validated on real sensor data obtained by our robot. It extends Viewpoint Feature Histograms (VFH), which classify unoccluded objects, to also classify partially occluded objects such as furniture that might be seen in typical office environments. To achieve this result, VPOD employs two strategies. First, object models are segmented and the object database is extended to include partial models. Second, once a matching partial object is detected, the complete object model is aligned back into the scene and verified for consistency with the point cloud data. Overall, our approach increases the number of objects found and substantially reduces false positives due to the verification process.

Multi-robot multi-object rearrangement in assignment space

We present Assignment Space Planning, a new efficient robot multi-agent coordination algorithm for the PSPACE-hard problem of multi-robot multi-object push rearrangement. In both simulated and real robot experiments, we demonstrate that our method produces optimal solutions for simple problems and exhibits novel emergent behaviors for complex scenarios. Assignment Space takes advantage of the domain structure by splitting the planning up into three stages, effectively reducing the search space size and enabling the planner to produce optimized plans in seconds. Our algorithm finds solutions of comparable quality to complete configuration space search while reducing the computing time to seconds, which allows our approach to be applied in practical scenarios in real-time.

Navigation Among Movable Obstacles with learned dynamic constraints

In this paper we present the first planner for the problem of Navigation Among Movable Obstacles (NAMO) on a real robot that can handle environments with under-specified object dynamics. This result makes use of recent progress from two threads of the Reinforcement Learning literature. The first is a hierarchical Markov-Decision Process formulation of the NAMO problem designed to handle dynamics uncertainty. The second is a physics-based Reinforcement Learning framework which offers a way to ground this uncertainty in a compact model space that can be efficiently updated from data received by the robot online. Our results demonstrate the ability of a robot to adapt to unexpected object behavior in a real office scenario.