Deeply Informed Neural Sampling for Robot Motion Planning

In this paper, we discuss the field of sampling-based motion planning. In contrast to methods that construct boundary representations of configuration space obstacles, samplingbased methods use only information from a collision detector as they search the configuration space. The simplicity of this approach, along with increases in computation power and the development of efficient collision detection algorithms, has resulted in the introduction of a number of powerful motion planning algorithms, capable of solving challenging problems with many degrees of freedom. First, we trace how sampling-based motion planning has developed. We then discuss a variety of important issues for sampling-based motion planning, including uniform and regular sampling, topological issues, and search philosophies. Finally, we address important issues regarding the role of randomization in sampling-based motion planning.

We discuss the optimality and computational efficiency of sampling based motion planning (SBMP), which calculates dynamically precise and approximately optimal state transitions using arbitrarily selected nonlinear control system models. To ensure high optimality and computational efficiency, SBMP requires an approximately uniform state sampling function, though the non-linearity of the system models does not allow a perfect function. We propose linear prediction-based uniform state sampling (LPUSS) that samples approximately uniform state points while ensuring a dynamically correct state transition profile with a small calculation cost. LPUSS samples a state by using the given non-linear control system model after determining the input values by using a local linear transition model. We developed a mechanical motion planning system using LPUSS, articulated body algorithm, and parallel computing techniques. To validate LPUSS, we conducted experiments on double, triple, and sixtuple inverted pendulum models. LPUSS showed better optimality and computational efficiency with the double and triple inverted pendulum models, compared with randomized kinodynamic planning (RKP), which is based on rapid random tree (RRT), and our previously proposed rapid semi-optimal motion-planning method in which state sampling is based on uniform inputs. In particular, compared with our previous method, LPUSS was respectively 130 times and 3,000 times faster on double and triple inverted pendulum models under the condition of the same optimality. LPUSS found an approximately optimal swing up motion for the sixtuple inverted pendulum model within 40 minutes. According to our survey, there is no other optimization method that is applicable to higher than quadruple inverted pendulum models with standard constraints.

In the Sampling-based motion planning, the collision checking procedure called many times and this operation takes the most planning time. The time spend in the collision checking increases with the number of obstacles. This paper aims to reduce the number of calls of the collision checking procedure in environment containing high number of obstacles. Our approach shows that the complexity of collision checking does not depend on the number of obstacles. The idea is to perform a pre-procedure that localizes the obstacles by segmenting the workspace into a grid and save it in a matrix form. This information is used in the collision checking procedure. We have used the Probabilistic Roadmaps (PRM) motion planner with a punctual robot and polygonal obstacles in 2D environment. Simulation results show the efficiency of our algorithm in reducing the complexity of collision checking and minimizing the planning time.

Haptic devices allow a user to feel either reaction forces from virtual interactions or reaction forces reflected from a remote site during a bilateral teleoperation task. Also, guiding forces can be exerted to train the user in the performance of a virtual task or to assist him/her to safely teleoperate a robot. The generation of guiding forces relies on the existence of a motion plan that provides the direction to be followed to reach the goal from any free configuration of the configuration space ( ${\mathcal C}$ -space). This paper proposes a method to obtain such a plan that interleaves a sampling-based exploration of ${\mathcal C}$ -space with an efficient computation of harmonic functions. A deterministic sampling sequence (with a bias based on harmonic function values) is used to obtain a hierarchical cell decomposition model of ${\mathcal C}$ -space. A harmonic function is iteratively computed over the partially known model using a novel approach. The harmonic function is the navigation function used as motion plan. The approach has been implemented in a planner (called the Kautham planner) that, given an initial and a goal configuration, provides: (a) a channel of cells connecting the cell that contains the initial configuration with the cell that contains the goal configuration; (b) two harmonic functions over the whole ${\mathcal C}$ -space, one that guides motions towards the channel and another that guides motions within the channel towards the goal; and (c) a path computed over a roadmap built with the free samples of the channel. The harmonic functions and the solution path are then used to generate the guiding forces for the haptic device. The planning approach is illustrated with examples on 2D and 3D workspaces.

One of the major components of Agent Based Crowd Simulation is motion planning. There have been various motion planning algorithms developed and they’ve become increasingly better and more efficient at calculating the most optimal path. We believe that this optimality is coming at the price of realism. Certain factors like social norms, limitations to human computation capabilities, etc. prevent humans from following their optimal path. One aspect of natural movement is related to perception and the manner in which humans process information. In this paper we propose two additions to general motion planning algorithms: (1) Group sensing for motion planning which results in agents avoiding clusters of other agents when choosing their collision free path. (2) Filtering of percepts based on interestingness to model limited information processing capabilities of human beings.KeywordsAgent-Based ModelSensingCrowd SimulationMotion PlanningVisual CognitionGroup Based PerceptionInformationCollision Avoidance

Sampling-based motion planning techniques have emerged as an efficient algorithmic paradigm for solving complex motion planning problems. These approaches use a set of probing samples to construct an implicit graph representation of the robot's state space, allowing arbitrarily accurate representations as the number of samples increases to infinity. In practice, however, solution trajectories only rely on a few critical states, often defined by structure in the state space (e.g., doorways). In this work we propose a general method to identify these critical states via graph-theoretic techniques (betweenness centrality) and learn to predict criticality from only local environment features. These states are then leveraged more heavily via global connections within a hierarchical graph, termed Critical Probabilistic Roadmaps. Critical PRMs are demonstrated to achieve up to three orders of magnitude improvement over uniform sampling, while preserving the guarantees and complexity of sampling-based motion planning. A video is available at https://youtu.be/AYoD-pGd9ms.

To compute collision-free and dynamically-feasibile trajectories that satisfy high-level specifications given in a planning-domain definition language, this paper proposes to combine sampling-based motion planning with symbolic action planning. The proposed approach, Sampling-based Motion and Symbolic Action Planner (SMAP), leverages from sampling-based motion planning the underlying idea of searching for a solution trajectory by selectively sampling and exploring the continuous space of collision-free and dynamically-feasible motions. Drawing from AI, SMAP uses symbolic action planning to identify actions and regions of the continuous space that sampling-based motion planning can further explore to significantly advance the search. The planning layers interact with each-other through estimates on the utility of each action, which are computed based on information gathered during the search. Simulation experiments with dynamical models of vehicles carrying out tasks given by high-level STRIPS specifications provide promising initial validation, showing that SMAP efficiently solves challenging problems.

Traditional motion planning can be computationally burdensome for practical robots, due to extensive collision checking and considerable iterative propagation of cost values. We present a novel neural network architecture which can directly generate the cost-to-go (c2g) function for a given configuration space and a goal configuration. The output of the network is a continuous function whose gradient in configuration space can be directly used to generate trajectories in motion planning without the need for protracted iterations or extensive collision checking. This higher order function (i.e. a function generating another function) representation lies at the core of our motion planning architecture, c2g-HOF, which can take a workspace as input, and generate the cost-to-go function over the configuration space map (C-map). Simulation results for 2D and 3D environments show that c2g-HOF can be orders of magnitude faster at execution time than methods which explore the configuration space during execution. We also present an implementation of c2g-HOF which generates trajectories for robot manipulators directly from an overhead image of the workspace.

One of the ultimate goals of mobile robotics research is to build robots that can safely carry out missions in hazardous and populated environments. Most of today's commercial mobile devices scale poorly along this dimension. Their motion planning relies on accurate, static models of the environments, and therefore they often fail their mission if humans or other unpredictable obstacles block their path. To build autonomous mobile robots one has to build systems that can perceive their environments, react to unforeseen circumstances, and plan dynamically in order to achieve their mission. Thus, the objective of the motion planning and control problem is to find collision-free trajectories, in static or dynamic environments containing some obstacles, between a start and a goal configuration. It has attracted much research in recent years. In this context the term control has a broad meaning that includes many different controls, such as low-level motor control, and behaviour control, where behaviour represents many complicated tasks, like obstacle avoidance and goal seeking. This article describes an intelligent motion planning and navigation system for omnidirectional mobile robots based on fuzzy logic. Owing to its simplicity and hence its short response time, the fuzzy navigator is especially suitable for on-line applications with strong real-time requirements. On-line planning is an on-going activity. The planner receives a continuous flow of information about occurring events and generates new commands in response to the incoming events, while previously planned motions are being executed. The fuzzy-rule-base of the proposed system combines the repelling influence, which is related to the distance and the angle between the robot and nearby obstacles, with the attracting influence produced by the distance and the angular difference between the actual direction and position of the robot and the final configuration, to generate actuating commands for the mobile platform. It can be considered as an on-line local navigation method for omnidirectional mobile robots for the generation of instantaneous collision-free motions. This reactive system is especially suitable for real-time applications. The use of fuzzy logic leads to a transparent system which can be tuned by hand or by a set of learning rules. Furthermore, this approach allows obstacle avoidance and navigation in dynamic environments. The functioning of the fuzzy motion planner with respect to omnidirectional mobile robots and results of simulated experiments are presented.

Sampling-based motion planning (SBMP) is a major trajectory planning approach in autonomous driving given its high efficiency in practice. As the core of SBMP schemes, sampling strategy holds the key to whether a smooth and collision-free trajectory can be found in real-time. Although some bias sampling strategies have been explored in the literature to accelerate SBMP, the trajectory generated under existing bias sampling strategies may lead to sharp lane changing. To address this issue, we propose a new learning framework for SBMP. Specifically, we develop a novel automatic labeling scheme and a 2-Stage prediction model to improve the accuracy in predicting the intention of surrounding vehicles. We then develop an imitation learning scheme to generate sample points based on the experience of human drivers. Using the prediction results, we design a new bias sampling strategy to accelerate the SBMP algorithm by strategically selecting necessary sample points that can generate a smooth and collision-free trajectory and avoid sharp lane changing. Data-driven experiments show that the proposed sampling strategy outperforms existing sampling strategies, in terms of the computing time, traveling time, and smoothness of the trajectory. The results also show that our scheme is even better than human drivers.

Steerable needles composed of a highly flexible material and with a bevel tip offer greater mobility compared to rigid needles for minimally invasive medical procedures. In this paper, we apply sampling-based motion planning technique to explore motion planning for the steerable bevel-tip needle in 3D environments with obstacles. Based on the Rapidly-exploring Random Trees (RRTs) method, we develop a motion planner to quickly build a tree to search the configuration space using a new exploring strategy, which generates new states using randomly sampled control space instead of the deterministically sampled one used in classic RRTs. Notice the fact that feasible paths might not be found for any given entry point and target configuration, we also address the feasible entry point planning problem to find feasible entry points in a specified entry zone for any given target configuration. To solve this problem, we developed a motion planning algorithm based on RRTs with backchaining, which grow backward from the target to explore the configuration space. Finally, simulation results with a approximated realistic prostate needle insertion environment demonstrate the performance of the proposed motion planner.

Asymptotically-optimal sampling-based motion planners, like RRT*, perform vast amounts of collision checking, and are hence rather slow to converge in complex problems where collision checking is relatively expensive. This paper presents two novel motion planners, Lazy-PRM* and Lazy-RRG*, that eliminate the majority of collision checks using a lazy strategy. They are sampling-based, any-time, and asymptotically complete algorithms that grow a network of feasible vertices connected by edges. Edges are not immediately checked for collision, but rather are checked only when a better path to the goal is found. This strategy avoids checking the vast majority of edges that have no chance of being on an optimal path. Experiments show that the new methods converge toward the optimum substantially faster than existing planners on rigid body path planning and robot manipulation problems.

Optimal paths in multi-stage stochastic decision networks

We present a novel approach to perform fast probabilistic collision checking in high-dimensional configuration spaces to accelerate the performance of sampling-based motion planning. Our formulation stores the results of prior collision queries, and then uses such information to predict the collision probability for a new configuration sample. In particular, we perform an approximate k-NN (k-nearest neighbor) search to find prior query samples that are closest to the new query configuration. The new query sample’s collision status is then estimated according to the collision checking results of these prior query samples, based on the fact that nearby configurations are likely to have the same collision status. We use locality-sensitive hashing techniques with sub-linear time complexity for approximate k-NN queries. We evaluate the benefit of our probabilistic collision checking approach by integrating it with a wide variety of sampling-based motion planners, including PRM (Probabilistic roadmaps), lazyPRM, RRT Rapidly exploring random trees, and RRT*. Our method can improve these planners in various manners, such as accelerating the local path validation, or computing an efficient order for the graph search on the roadmap. Experiments on a set of benchmarks demonstrate the performance of our method, and we observe up to 2x speedup in the performance of planners on rigid and articulated robots.

In this work we present a methodology for intelligent motion planning in an uncertain environment using a non-local sensor, such as radar. This methodology is applied to an unmanned helicopter navigating a cluttered urban environment. We show that the problem of motion planning in a uncertain environment, under certain assumptions, can be posed as the adaptive optimal control of an uncertain Markov decision process, characterized by a known, control dependent system, and an unknown, control independent environment. The strategy for motion planning then reduces to computing the control policy based on the current estimate of the environment, also known as the "certainty equivalence principle" in the adaptive control literature. Our methodology allows the inclusion of a non-local sensor into the problem formulation, which significantly accelerates the convergence of the estimation and planning algorithms. Further we show that the motion planning and estimation problems, as formulated in this paper possess special structure which can be exploited to significantly reduce the computational burden of the associated algorithms. We apply this methodology to the problem of motion planning for an unmanned helicopter in a partially known model of the Texas A&M campus