Mihail Pivtoraiko

CHOMP: Covariant Hamiltonian optimization for motion planning

In this paper, we present CHOMP (covariant Hamiltonian optimization for motion planning), a method for trajectory optimization invariant to reparametrization. CHOMP uses functional gradient techniques to iteratively improve the quality of an initial trajectory, optimizing a functional that trades off between a smoothness and an obstacle avoidance component. CHOMP can be used to locally optimize feasible trajectories, as well as to solve motion planning queries, converging to low-cost trajectories even when initialized with infeasible ones. It uses Hamiltonian Monte Carlo to alleviate the problem of convergence to high-cost local minima (and for probabilistic completeness), and is capable of respecting hard constraints along the trajectory. We present extensive experiments with CHOMP on manipulation and locomotion tasks, using seven-degree-of-freedom manipulators and a rough-terrain quadruped robot.

Generating near minimal spanning control sets for constrained motion planning in discrete state spaces

We propose a principled method to create a search space for constrained motion planning, which efficiently encodes only feasible motion plans. The space of possible paths is encoded implicitly in the connections between states, but only feasible and only local connections are allowed. Furthermore, we propose a systematic method to generate a near-minimal set of spatially distinct motion alternatives. This set of motion primitives preserves the connectivity of the representation while eliminating redundancy - leading to a very efficient structure for motion planning at the chosen resolution.

An integrated system for autonomous robotics manipulation

We describe the software components of a robotics system designed to autonomously grasp objects and perform dexterous manipulation tasks with only high-level supervision. The system is centered on the tight integration of several core functionalities, including perception, planning and control, with the logical structuring of tasks driven by a Behavior Tree architecture. The advantage of the implementation is to reduce the execution time while integrating advanced algorithms for autonomous manipulation. We describe our approach to 3-D perception, real-time planning, force compliant motions, and audio processing. Performance results for object grasping and complex manipulation tasks of in-house tests and of an independent evaluation team are presented.

Model-Predictive Motion Planning: Several Key Developments for Autonomous Mobile Robots

A necessary attribute of a mobile robot planning algorithm is the ability to accurately predict the consequences of robot actions to make informed decisions about where and how to drive. It is also important that such methods are efficient, as onboard computational resources are typically limited and fast planning rates are often required. In this article, we present several practical mobile robot motion planning algorithms for local and global search, developed with a common underlying trajectory generation framework for use in model-predictive control. These techniques all center on the idea of generating informed, feasible graphs at scales and resolutions that respect computational and temporal constraints of the application. Connectivity in these graphs is provided by a trajectory generator that searches in a parameterized space of robot inputs subject to an arbitrary predictive motion model. Local search graphs connect the currently observed state-to-states at or near the planning or perception horizon. Global search graphs repeatedly expand a precomputed trajectory library in a uniformly distributed state lattice to form a recombinant search space that respects differential constraints. In this article, we discuss the trajectory generation algorithm, methods for online or offline calibration of predictive motion models, sampling strategies for local search graphs that exploit global guidance and environmental information for real-time obstacle avoidance and navigation, and methods for efficient design of global search graphs with attention to optimality, feasibility, and computational complexity of heuristic search. The model-invariant nature of our approach to local and global motions planning has enabled a rapid and successful application of these techniques to a variety of platforms. Throughout the article, we also review experiments performed on planetary rovers, field robots, mobile manipulators, and autonomous automobiles and discuss future directions of the article.

Kinodynamic motion planning with state lattice motion primitives

This paper presents a type of motion primitives that can be used for building efficient kinodynamic motion planners. The primitives are pre-computed to meet two objective: to capture the mobility constraints of the robot as well as possible and to establish a state sampling policy that is conductive to efficient search. The first objective allows encoding mobility constraints into primitives, thereby enabling fast unconstrained search to produce feasible solutions. The second objective enables high quality (lattice) sampling of state space, further speeding up exploration during search. We further discuss several novel results enabled by using such motion primitives for kinodynamic planning, including incremental search, efficient bi-directional search and incremental sampling.

A Computationally Efficient Approach to Trajectory Management for Coordinated Aerial Surveillance

Time optimal path planning and trajectory management algorithms for air vehicles with limited on-board computing resources require an efficient approach to satisfy flight dynamic constraints needed to guarantee paths are feasible. B-spline curves enable compact definition of feasible airplane trajectories that are suited for on-board real-time computation. The design of a trajectory definition and management algorithm suited for a multi-agent persistent surveillance application is described. The proposed solution post-processes the output of a point-by-point path planner and converts it into a minimal representation. Key design requirements include minimization of mission execution time, ability to seamlessly redirect agents based on information acquired by sensor feedback, and robust adherence to mission and vehicle motion constraints. A simple coordinated aerial surveillance scenario is described and demonstrated using the algorithms presented.

Incremental micro-UAV motion replanning for exploring unknown environments

This paper describes an approach to motion generation for quadrotor micro-UAVs navigating cluttered and partially known environments. We pursue a graph search method that, despite the high dimensionality of the problem, the complex dynamics of the system and the continuously changing environment model is capable of generating dynamically feasible motions in real-time. This is enabled by leveraging the differential flatness property of the system and by developing a structured search space based on state lattice motion primitives. We suggest a greedy algorithm to generate these primitives off-line automatically, given the robots motion model. The process samples the reachability of the system and reduces it to a set of representative, canonical motions that are compatible with the state lattice structure, which guarantees that any incremental replanning algorithm is able to produce smooth dynamically feasible motion plans while reusing previous computation between replans. Simulated and physical experimental results demonstrate real-time replanning due to the inevitable and frequent world model updates during micro-UAV motion in partially known environments.

Differentially constrained motion replanning using state lattices with graduated fidelity

This paper presents an approach to differentially constrained robot motion planning and efficient re-planning. Satisfaction of differential constraints is guaranteed by the state lattice, a search space which consists of motions that satisfy the constraints by construction. Any systematic replanning algorithm, e.g. D*, can be utilized to search the state lattice to find a motion plan that satisfies the differential constraints, and to repair it efficiently in the event of a change in the environment. Further efficiency is obtained by varying the fidelity of representation of the planning problem. High fidelity is utilized where it matters most, while it is lowered in the areas that do not affect the quality of the plan significantly. The paper presents a method to modify the fidelity between replans, thereby enabling dynamic flexibility of the search space, while maintaining its compatibility with replanning algorithms. The approach is especially suited for mobile robotics applications in unknown challenging environments. In this setting, we applied the planner successfully to the navigation of research prototype rovers in JPL Mars Yard.

Constrained Motion Planning in Discrete State Spaces

We propose a principled method to create a search space for constrained motion planning, which efficiently encodes only feasible motion plans. The space of possible paths is encoded implicitly in the connections between states, but only feasible and only local connections are allowed. Furthermore, we propose a systematic method to generate a near-minimal set of spatially distinct motion alternatives. This set of motion primitives preserves the connectivity of the representation while eliminating redundancy — leading to a very efficient structure for motion planning at the chosen resolution.

Autonomous robot navigation using advanced motion primitives

We present an approach to efficient navigation of autonomous wheeled robots operating in cluttered natural environments. The approach builds upon a popular method of autonomous robot navigation, where desired robot motions are computed using local and global motion planners operating in tandem. A conventional approach to designing the local planner in this setting is to evaluate a fixed number of constant-curvature arc motions and pick one that is the best balance between the quality of obstacle avoidance and minimizing traversed path length to the goal (or a similar measure of operation cost). The presented approach proposes a different set of motion alternatives considered by the local planner. Important performance improvement is achieved by relaxing the assumption that motion alternatives are constant-curvature arcs. We first present a method to measure the quality of local planners in this setting. Further, we identify general techniques of designing improved sets of motion alternatives. By virtue of a minor modification, solely replacing the motions considered by the local planner, our approach offers a measurable performance improvement of dual-planner navigation systems.