Adaptive Lazy Collision Checking for Optimal Sampling-based 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.

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.

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.

Collision detection is a critical problem in multi-axis NC machining with complex machining environments. Using a combination of machining environment culling and a two-phase collision detection strategy, a rapid and robust collision detection approach is implemented. With this approach, the machining environment is initially subdivided and organized hierarchically using a binary space partitioning (BSP) tree structure. Before carrying out precise collision detection, the machining environment is culled conservatively to remove most of the irrelevant geometries from further checking steps which are relatively time consuming. For the later stage of precise collision detection, which is the most complicated and time-consuming task in many existing approaches, a strategy of using two-phase collision detection is developed in order to make the approach not only efficient in computation and but also maintain a high detection precision at the same time. Another important benefit of this approach is that it takes advantage of the rapid performance of graphics hardware to generate visibility information very efficiently. We show how this information could be used in assisting collision detection. An example of five-axis machining in a complex environment is adopted as the case study to demonstrate the proposed approach. It has shown that the collision detection task can be achieved with a near real-time performance.

Chapter 8 - Probabilistic roadmap

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.

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.

A recent trend in optimal motion planning has broadened the research area toward the hybridization of sampling, optimization and grid-based approaches. We can expect that synergy from such integrations leads to overall performance improvement, but seamless integration and generalization is still an open problem. In this paper, we suggest a hybrid motion planning algorithm utilizing a sampling-based and optimization-based planner while simultaneously approximating a configuration free space. Unlike conventional optimization-based approaches, the proposed algorithm does not depend on a priori information or resolution-complete factors, e.g., a distance field. Ours instead learns spatial information on the fly by exploiting empirical information during the execution, and decentralizes the information over the constructed graph for efficient access. With the help of the learned information, our optimization-based local planner exploits the local area to identify the connectivity of configuration free space without depending on the precomputed domain knowledge. To show the novelty of proposed algorithm, we evaluate it against other asymptotic optimal planners in both synthetic and complex benchmarks with varying degrees of freedom. We also discuss the performance improvement, properties and limitations we have observed.

In this paper, we propose an image-based collision detection optimization algorithm in order to meet the high requirements of real-time and accuracy in the increasingly complex collision detection environment. The algorithm can deal with arbitrary model and will make efficient use of the GPU on the basis of RECODE and RAPID algorithm. In this paper, the algorithm flow will be divided into two stages: the pre-processing stage and the real-time collision detection stage. We will focus on the real-time collision detection stage in this paper. Experimental results show that the algorithm effectively reduces the average collision time compared to RECODE and RAPID algorithm.

This paper develops a tool path optimization method for robotic surface machining by sampling-based motion planning algorithms. In the surface machining process, the tool-tip position needs to strictly follow the tool path curve and the posture of the tool axis should be limited in a certain range. But the industrial robot has at least six degrees-of-freedom (Dof) and has redundant Dofs for surface machining. Therefore, the tool motion of surface machining can be optimized using the redundant Dofs considering the tool path constraints and limits of the tool axis orientation. Due to the complexity of the problem, the sampling-based motion planning method has been chosen to find the solution, which randomly explores the configuration space of the robot and generates a discrete path of valid robot state. During the solving process, the joint space of the robot is chosen as the configuration space of the problem and the constraints for the tool-tip following requirements are in the operation space. Combined with general collision checking, the limited region of the tool axis vector is used to verify the state’s validity of the configuration space. In the optimization process, the sum of the path length of each joint of the robot is set as the optimization objective. The algorithm is developed based on the open motion planning library (OMPL), which contains the state-of-the-art sampling-based motion planners. Finally, two examples are used to demonstrate the effiectiveness and optimality of the method.

Sampling-based motion planning algorithms have been successfully applied to various types of high-dimensional planning tasks. Recently an extension of PRM algorithm called PRM* planner has been proposed which guarantees asymptotic optimal solutions in terms of path length. However, the high runtime of sampling-based algorithms is still a serious disadvantage. In this paper, a new extension of PRM planner is proposed which incorporates the variable neighborhood radius feature of PRM* and the sampling radius of low-dispersion sampling in order to improve the cost of the generated solutions in terms of path length and runtime. The performance of the proposed algorithm is tested in different planning environments. Furthermore, the proposed planner is compared to the original PRM and the PRM* approaches and shows significant improvement.

For safe last‐mile autonomous robot delivery services in complex environments, rapid and accurate collision prediction and detection is vital. This study proposes a suitable neural network model that relies on multiple navigation sensors. A light detection and ranging technique is used to measure the relative distances to potential collision obstacles along the robot's path of motion, and an accelerometer is used to detect impacts. The proposed method tightly couples relative distance and acceleration time‐series data in a complementary fashion to minimize errors. A long short‐term memory, fully connected layer, and SoftMax function are integrated to train and classify the rapidly changing collision countermeasure state during robot motion. Simulation results show that the proposed method effectively performs collision prediction and detection for various obstacles.

Sampling-based Motion Planners (SMPs) have become increasingly popular as they provide collision-free path solutions regardless of obstacle geometry in a given environment. However, their computational complexity increases significantly with the dimensionality of the motion planning problem. Adaptive sampling is one of the ways to speed up SMPs by sampling a particular region of a configuration space that is more likely to contain an optimal path solution. Although there are a wide variety of algorithms for adaptive sampling, they rely on hand-crafted heuristics; furthermore, their performance decreases significantly in high-dimensional spaces. In this paper, we present a neural network-based adaptive sampler for motion planning called Deep Sampling-based Motion Planner (DeepSMP). DeepSMP generates samples for SMPs and enhances their overall speed significantly while exhibiting efficient scalability to higher-dimensional problems. DeepSMP's neural architecture comprises of a Contractive AutoEncoder which encodes given workspaces directly from a raw point cloud data, and a Dropout-based stochastic deep feedforward neural network which takes the workspace encoding, start and goal configuration, and iteratively generates feasible samples for SMPs to compute end-to-end collision-free optimal paths. DeepSMP is not only consistently computationally efficient in all tested environments but has also shown remarkable generalization to completely unseen environments. We evaluate DeepSMP on multiple planning problems including planning of a point-mass robot, rigid-body, 6-link robotic manipulator in various 2D and 3D environments. The results show that on average our method is at least 7 times faster in point-mass and rigid-body case and about 28 times faster in 6-link robot case than the existing state-of-the-art.

Collision-free motion planning allows robots to perform tasks in complex environments, but the conservative bounding curves during collision detection will reduce the robot's dexterity. This paper presents a novel algorithm for real-time motion planning of non-holonomic robots in dynamic scenes. To achieve this, the robot and the obstacles are generally decomposed into a series of superquadric objects. The expanded closed-form Minkowski sums are used to construct the velocity obstacle to deal with the updating orientation of the robot. The algorithm is extended to collision avoidance for different numbers and types of obstacles, which share the same workspace with the robot. We implement our algorithm in various simulations and experiments, where the robot has to avoid collisions with obstacles in real-time. The results demonstrate the effectiveness and efficiency of the proposed algorithm in collision-free motion planning at real-time computation rates and the enhanced dexterity control in complex environments.

Motion planning for humanoid robotic systems with many degrees of freedom is an important and still generally unsolved problem. To give the robot the ability of acting and navigating in complex environments, the motion planner has to find collision-free paths in a robust manner. The runtime of a planning algorithm is critical, since complex tasks require several planning steps where the collision detection and avoidance should be accomplished in reasonable time. In this paper we present an extension of standard sampling-based techniques using Rapidly Exploring Random Trees (RRT). We extend the free-bubble path validation algorithm from Quinlan, which can be used to guarantee the collision-free status of a C-space path between two samples. By using enlarged robot models it is possible to avoid costly distance calculations and therefore to speed up the planning process. We also present a combined approach based on lazy collision checking that brings together the advantages of fast sampling-based and exact path-validated algorithms. The proposed algorithms have been evaluated by experiments on a humanoid robot in a kitchen environment and by a comparison to a validation based on Quinlan's free bubbles approach.