We present demonstration-guided motion planning (DGMP), a new framework for planning motions for personal robots to perform household tasks. DGMP combines the strengths of sampling-based motion planning and robot learning from demonstrations to generate plans that (1) avoid novel obstacles in cluttered environments, and (2) learn and maintain critical aspects of the motion required to successfu...

Mobility of sensors can be used to improve the information content of measurements when observing a dynamical system. However, as is shown in this paper, the sensor’s motion may, in fact, lead to increased worst-case estimation error. This paper investigates the relationship between the motion of the sensor and the performance of the observability grammian-based estimator, and provides a motion...

This paper is concerned with motion planning for non-linear robotic systems operating in constrained environments. A method for computing high-quality trajectories is proposed building upon recent developments in sampling-based motion planning and stochastic optimization. The idea is to equip sampling-based methods with a probabilistic model that serves as a sampling distribution and to increme...

We present a simple and natural extension of the multi-robot motion planning problem where the robots are partitioned into groups (colors), such that in each group the robots are interchangeable. Every robot is no longer required to move to a specific target, but rather to some target placement that is assigned to its group. We call this problem k-color multi-robot motion planning and provide a...

For robotic vehicles to navigate safely and efficiently in pedestrian-rich environments, it is important to model subtle human behaviors and navigation rules. However, while instinctive to humans, socially compliant navigation is still difficult to quantify due to the stochasticity in people’s behaviors. Existing works are mostly focused on using featurematching techniques to describe and imita...

where g1(x), . . . , gr(x) span R for all x. Note that r may be greater than m. This is because the vector fields are a function of position, and there may not be a fixed set of m brackets that span R ∀x. For an example, see [1], page 238. The new inputs v are referred to as fictitious inputs, because the v’s corresponding to the gi, i > m do not correspond to real inputs. Further, we require t...

Robotic motion planning requires configuration space exploration. In high-dimensional configuration spaces, a complete exploration is computationally intractable. To devise practical motion planning algorithms in such high-dimensional spaces, computational resources have to be expended in proportion to the local complexity of a configuration space region. We propose a novel motion planning appr...

This paper demonstrates an application of algebraic geometry to the real problem of robotic motion planning. We model an abstract robot arm using a system of polynomial equations specifying constraints imposed by the arm’s various linkages, and demonstrate techniques for solving them in common situations.

This paper presents an approach to differentially constrained robot motion planning and efficient replanning. Satisfaction of differential constraints is guaranteed by the 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 different...

The performance of a motion planning algorithm is intrinsically linked with applications that respect the assumptions being made. However, the mapping of these assumptions to actual environments is not always transparent. For example, a gradient descent algorithm is capable of tackling a complex optimization problem if some assurance of absence of bad local minimas can be ensured however detect...