Showing papers by "Brian C. Williams published in 2011"

Chance-Constrained Optimal Path Planning With Obstacles

Abstract: Autonomous vehicles need to plan trajectories to a specified goal that avoid obstacles. For robust execution, we must take into account uncertainty, which arises due to uncertain localization, modeling errors, and disturbances. Prior work handled the case of set-bounded uncertainty. We present here a chance-constrained approach, which uses instead a probabilistic representation of uncertainty. The new approach plans the future probabilistic distribution of the vehicle state so that the probability of failure is below a specified threshold. Failure occurs when the vehicle collides with an obstacle or leaves an operator-specified region. The key idea behind the approach is to use bounds on the probability of collision to show that, for linear-Gaussian systems, we can approximate the nonconvex chance-constrained optimization problem as a disjunctive convex program. This can be solved to global optimality using branch-and-bound techniques. In order to improve computation time, we introduce a customized solution method that returns almost-optimal solutions along with a hard bound on the level of suboptimality. We present an empirical validation with an aircraft obstacle avoidance example.

Improved human-robot team performance using chaski, a human-inspired plan execution system

Abstract: We describe the design and evaluation of Chaski, a robot plan execution system that uses insights from human-human teaming to make human-robot teaming more natural and fluid. Chaski is a task-level executive that enables a robot to collaboratively execute a shared plan with a person. The system chooses and schedules the robot's actions, adapts to the human partner, and acts to minimize the human's idle time.We evaluate Chaski in human subject experiments in which a person works with a mobile and dexterous robot to collaboratively assemble structures using building blocks. We measure team performance outcomes for robots controlled by Chaski compared to robots that are verbally commanded, step-by-step by the human teammate. We show that Chaski reduces the human's idle time by 85%, a statistically significant difference. This result supports the hypothesis that human-robot team performance is improved when a robot emulates the effective coordination behaviors observed in human teams.

Drake: an efficient executive for temporal plans with choice

Abstract: This work presents Drake, a dynamic executive for temporal plans with choice. Dynamic plan execution strategies allow an autonomous agent to react quickly to unfolding events, improving the robustness of the agent. Prior work developed methods for dynamically dispatching Simple Temporal Networks, and further research enriched the expressiveness of the plans executives could handle, including discrete choices, which are the focus of this work. However, in some approaches to date, these additional choices induce significant storage or latency requirements to make flexible execution possible. Drake is designed to leverage the low latency made possible by a preprocessing step called compilation, while avoiding high memory costs through a compact representation. We leverage the concepts of labels and environments, taken from prior work in Assumption-based Truth Maintenance Systems (ATMS), to concisely record the implications of the discrete choices, exploiting the structure of the plan to avoid redundant reasoning or storage. Our labeling and maintenance scheme, called the Labeled Value Set Maintenance System, is distinguished by its focus on properties fundamental to temporal problems, and, more generally, weighted graph algorithms. In particular, the maintenance system focuses on maintaining a minimal representation of non-dominated constraints. We benchmark Drake's performance on random structured problems, and find that Drake reduces the size of the compiled representation by a factor of over 500 for large problems, while incurring only a modest increase in run-time latency, compared to prior work in compiled executives for temporal plans with discrete choices.

Motion learning in variable environments using probabilistic flow tubes

Abstract: Commanding an autonomous system through complex motions at a low level can be tedious or impractical for systems with many degrees of freedom. Allowing an operator to demonstrate the desired motions directly can often enable more intuitive and efficient interaction. Two challenges in the field of learning from demonstration include (1) how to best represent learned motions to accurately reflect a human's intentions, and (2) how to enable learned motions to be easily applicable in new situations. This paper introduces a novel representation of continuous actions called probabilistic flow tubes that can provide flexibility during execution while robustly encoding a human's intended motions. Our approach also automatically determines certain qualitative characteristics of a motion so that these characteristics can be preserved when autonomously executing the motion in a new situation. We demonstrate the effectiveness of our motion learning approach both in a simulated two-dimensional environment and on the All-Terrain Hex-Limbed Extra-Terrestrial Explorer (ATHLETE) robot performing object manipulation tasks.

Hybrid planning with temporally extended goals for sustainable ocean observing

Abstract: A challenge to modeling and monitoring the health of the ocean environment is that it is largely under sensed and difficult to sense remotely. Autonomous underwater vehicles (AUVs) can improve observability, for example of algal bloom regions, ocean acidification, and ocean circulation. This AUV paradigm, however, requires robust operation that is cost effective and responsive to the environment. To achieve low cost we generate operational sequences automatically from science goals, and achieve robustness by reasoning about the discrete and continuous effects of actions. We introduce Kongming2, a generative planner for hybrid systems with temporally extended goals (TEGs) and temporally flexible actions. It takes as input high-level goals and outputs trajectories and actions of the hybrid system, for example an AUV. Kongming2 makes two major extensions to Kongming1: planning for TEGs, and planning with temporally flexible actions. We demonstrated a proof of concept of the planner in the Atlantic ocean on Odyssey IV, an AUV designed and built by the MIT AUV Lab at Sea Grant.

Flexible execution of plans with choice and uncertainty

Abstract: Dynamic plan execution strategies allow an autonomous agent to respond to uncertainties, while improving robustness and reducing the need for an overly conservative plan. Executives have improved robustness by expanding the types of choices made dynamically, such as selecting alternate methods. However, in some approaches to date, these additional choices often induce significant storage requirements to make flexible execution possible. This paper presents a novel system called Drake, which is able to dramatically reduce the storage requirements in exchange for increased execution time for some computations. Drake frames a plan as a collection of related Simple Temporal Problems, and executes the plan with a fast dynamic scheduling algorithm. This scheduling algorithm leverages prior work in Assumption-based Truth Maintenance Systems to compactly record and reason over the family of Simple Temporal Problems. We also allow Drake to reason over temporal uncertainty and choices by using prior work in Simple Temporal Problems with Uncertainty, which can guarantee correct execution, regardless of the uncertain outcomes. On randomly generated structured plans with choice, framed as either Temporal Plan Networks or Disjunctive Temporal Problems, we show a reduction in the size of the solution set of around four orders of magnitude, compared to prior art.

Regression-based LP solver for chance-constrained finite horizon optimal control with nonconvex constraints

Abstract: This paper presents a novel algorithm for finite-horizon optimal control problems subject to additive Gaussian-distributed stochastic disturbance and chance constraints that are defined over feasible, non-convex state spaces. Our previous work [1] proposed a branch and bound-based algorithm that can find a near-optimal solution by iteratively solving non-linear convex optimization problems, as well as their LP relaxations called Fixed Risk Relaxation (FRR) problems. The aim of this work is to significantly reduce the computation time of the previous algorithm so that it can be applied to practical problems, such as a path planning with multiple obstacles. Our approach is to use machine learning to efficiently estimate the objective function values of FRRs within an error bound that is fixed for a given problem domain and choice of model complexity. We exploit the fact that all the FRR problems associated with the branch-and-bound tree nodes are similar to each other, both in terms of the solutions as well as the objective function and constraint coefficients. A standard optimizer is first used to generate a training data set in the form of optimal FRR solutions. Matrix transformations and boosting trees are then applied to generate learning models; fast inference is performed at run-time for new but similar FRR problems that occur when the system dynamics and/or the environment changes slightly. By using this regression technique to estimate the lower bound of the cost function value, and subsequently solving the convex optimization problems exactly at the leaf nodes of the branch-and-bound tree, we achieve 10–35 times reduction in the computation time without compromising the optimality of the solution.

Compliant Task Execution and Learning for Safe Mixed-Initiative Human-Robot Operations

Abstract: We introduce a novel task execution capability that enhances the ability of in-situ crew members to function independently from Earth by enabling safe and efficient interaction with automated systems. This task execution capability provides the ability to (1) map goal-directed commands from humans into safe, compliant, automated actions, (2) quickly and safely respond to human commands and actions during task execution, and (3) specify complex motions through teaching by demonstration. Our results are applicable to future surface robotic systems, and we have demonstrated these capabilities on JPL's All-Terrain Hex-Limbed Extra-Terrestrial Explorer (ATHLETE) robot.