This paper presents an approach for learning vision-based planners that provably generalize to novel environments (i.e., environments unseen during training). We leverage the Probably Approximately Correct (PAC)-Bayes framework to obtain an upper bound on the expected cost of policies across all environments. Minimizing the PAC-Bayes upper bound thus trains policies that are accompanied by a certificate of performance on novel environments. The training pipeline we propose provides strong generalization guarantees for deep neural network policies by (a) obtaining a good prior distribution on the space of policies using Evolutionary Strategies (ES) followed by (b) formulating the PAC-Bayes optimization as an efficiently-solvable parametric convex optimization problem. We demonstrate the efficacy of our approach for producing strong generalization guarantees for learned vision-based motion planners through two simulated examples: (1) an Unmanned Aerial Vehicle (UAV) navigating obstacle fields with an onboard vision sensor, and (2) a dynamic quadrupedal robot traversing rough terrains with proprioceptive and exteroceptive sensors.
The functional demands of robotic systems often require completing various tasks or behaviors under the effect of disturbances or uncertain environments. Of increasing interest is the autonomy for dynamic robots, such as multirotors, motor vehicles, and legged platforms. Here, disturbances and environmental conditions can have significant impact on the successful performance of the individual dynamic behaviors, referred to as "motion primitives". Despite this, robustness can be achieved by switching to and transitioning through suitable motion primitives. This paper contributes such a method b…
We present a hierarchical framework for motion planning of a large collection of agents. The proposed framework starts from low level motion primitives over a gridded workspace and provides a set of rules for constructing higher level motion primitives. Our hierarchical approach is highly scalable and robust making it an ideal tool for planning for multi-agent systems. Results are demonstrated experimentally on a collection of quadrotors that must navigate a cluttered environment while maintaining a formation.
This paper presents an approach for learning motion planners that are accompanied with probabilistic guarantees of success on new environments that hold uniformly for any disturbance to the robot's dynamics within an admissible set. We achieve this by bringing together tools from generalization theory and robust control. First, we curate a library of motion primitives where the robustness of each primitive is characterized by an over-approximation of the forward reachable set, i.e., a "funnel". Then, we optimize probably approximately correct (PAC)-Bayes generalization bounds for training our …
Within the context of trajectory planning for autonomous vehicles this paper proposes methods for efficient encoding of motion primitives in neural networks on top of model-based and gradient-free reinforcement learning. It is distinguished between 5 core aspects: system model, network architecture, training algorithm, training tasks selection and hardware/software implementation. For the system model, a kinematic (3-states-2-controls) and a dynamic (16-states-2-controls) vehicle model are compared. For the network architecture, 3 feedforward structures are compared including weighted skip con…
Trained humans exhibit highly agile spatial skills, enabling them to operate vehicles with complex dynamics in demanding tasks and conditions. Prior work shows that humans achieve this performance by using strategies such as satisficing, learning hierarchical task structure, and using a library of motion primitive elements. A key aspect of efficient and versatile solutions is the decomposition of a task into a sequence of smaller tasks, represented by subgoals. The present work uses properties of constrained optimal control theory to define conditions that specify candidate subgoal states and …
University of Illinois at Urbana-Champaign（伊利诺伊大学厄巴纳-香槟分校）
In this work, we have implemented a SLAM-assisted navigation module for a real autonomous vehicle with unknown dynamics. The navigation objective is to reach a desired goal configuration along a collision-free trajectory while adhering to the dynamics of the system. Specifically, we use LiDAR-based Hector SLAM for building the map of the environment, detecting obstacles, and for tracking vehicle's conformance to the trajectory as it passes through various states. For motion planning, we use rapidly exploring random trees (RRTs) on a set of generated motion primitives to search for dynamically …
Towards High Efficient Long-horizon Planning with Expert-guided Motion-encoding Tree Search
The Chinese University of Hong Kong（香港中文大学）；Macao Polytechnic University（澳门理工大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Southern University of Science and Technology（南方科技大学）
INRIA（法国国家信息与自动化研究所）；École normale supérieure（巴黎高等师范学院）；CNRS（法国国家科学研究中心）；PSL Research University（巴黎文理研究大学）；New York University（纽约大学）
This paper addresses the problem of copying an unknown assembly of primitives with known shape and appearance using information extracted from a single photograph by an off-the-shelf procedure for object detection and pose estimation. The proposed algorithm uses a simple combination of physical stability constraints, convex optimization and Monte Carlo tree search to plan assemblies as sequences of pick-and-place operations represented by STRIPS operators. It is efficient and, most importantly, robust to the errors in object detection and pose estimation unavoidable in any real robotic system.…
Search-based planning with motion primitives is a powerful motion planning technique that can provide dynamic feasibility, optimality, and real-time computation times on size, weight, and power-constrained platforms in unstructured environments. However, optimal design of the motion planning graph, while crucial to the performance of the planner, has not been a main focus of prior work. This paper proposes to address this by introducing a method of choosing vertices and edges in a motion primitive graph that is grounded in sampling theory and leads to theoretical guarantees on planner complete…
This manuscript presents enhancements on our motion-primitives exploration path planning method for agile exploration using aerial robots. The method now further integrates a global planning layer to facilitate reliable large-scale exploration. The implemented bifurcation between local and global planning allows for efficient exploration combined with the ability to plan within very large environments, while also ensuring safe and timely return-to-home. A new set of simulation studies and experimental results are presented to demonstrate the new improvements and enhancements. The method is ava…
A*STAR Artificial Intelligence Initiative (A*AI)（新加坡科技研究局人工智能计划（A*AI））；Institute of High Performance Computing（高性能计算研究所）；Carnegie Mellon University（卡内基梅隆大学）
Planning the path to gather the surface information of the target objects is crucial to improve the efficiency of and reduce the overall cost, for visual inspection applications with Unmanned Aerial Vehicles (UAVs). Coverage Path Planning (CPP) problem is often formulated for these inspection applications because of the coverage requirement. Traditionally, researchers usually plan and optimize the viewpoints to capture the surface information first, and then optimize the path to visit the selected viewpoints. In this paper, we propose a novel planning method to directly sample and plan the ins…
We present an approach that generates kinodynamically feasible paths for robots using Rapidly-exploring Random Tree (RRT). We leverage motion primitives as a way to capture the dynamics of the robot and use these motion primitives to build branches of the tree with RRT. Since every branch is built using the robot's motion primitives that doesn't lead to collision with obstacles, the resulting path is guaranteed to satisfy the robot's kinodynamic constraints and thus be feasible for navigation without any post-processing on the generated trajectory. We demonstrate the effectiveness of our appro…
Rapidly exploring random trees (RRTs) have proven effective in quickly finding feasible solutions to complex motion planning problems. RRT* is an extension of the RRT algorithm that provides probabilistic asymptotic optimality guarantees when using straight-line motion primitives. This work provides extensions to RRT and RRT* that employ fillets as motion primitives, allowing path curvature constraints to be considered when planning. Two fillets are developed, an arc-based fillet that uses circular arcs to generate paths that respect maximum curvature constraints and a spline-based fillet that…
Using Implicit Behavior Cloning and Dynamic Movement Primitive to Facilitate Reinforcement Learning for Robot Motion Planning
Eindhoven University of Technology（埃因霍温理工大学）；University of Victoria（维多利亚大学）；Natural Sciences and Engineering Research Council (NSERC) Canada（加拿大自然科学与工程研究委员会）
Multi-Robot Motions in Milliseconds: Vector-Accelerated Primitives for Sampling-Based Planning
Parasol Lab, School of Computing and Data Science, University of Illinois at Urbana Champaign（帕索尔实验室，计算与数据科学学院，伊利诺伊大学厄巴纳-香槟分校）；Department of Computer Science at Instituto Tecnológico Autónomo de México (ITAM)（墨西哥自治理工学院（ITAM）计算机科学系）
Beijing Institute of Technology（北京理工大学）；CNRS-UM LIRMM（法国国家科学研究中心-蒙彼利埃大学机器人与微电子实验室）
Developing an intelligent vehicle which can perform human-like actions requires the ability to learn basic driving skills from a large amount of naturalistic driving data. The algorithms will become efficient if we could decompose the complex driving tasks into motion primitives which represent the elementary compositions of driving skills. Therefore, the purpose of this paper is to segment unlabeled trajectory data into a library of motion primitives. By applying a probabilistic inference based on an iterative Expectation-Maximization algorithm, our method segments the collected trajectories …
The discontinuities and multi-modality introduced by contacts make manipulation planning challenging. Many previous works avoid this problem by pre-designing a set of high-level motion primitives like grasping and pushing. However, such motion primitives are often not adequate to describe dexterous manipulation motions. In this work, we propose a method for dexterous manipulation planning at a more primitive level. The key idea is to use contact modes to guide the search in a sampling-based planning framework. Our method can automatically generate contact transitions and motion trajectories un…
In this paper, we approach the challenging problem of motion planning for knot tying. We propose a hierarchical approach in which the top layer produces a topological plan and the bottom layer translates this plan into continuous robot motion. The top layer decomposes a knotting task into sequences of abstract topological actions based on knot theory. The bottom layer translates each of these abstract actions into robot motion trajectories through learned topological motion primitives. To adapt each topological action to the specific rope geometry, the motion primitives take the observed rope …
Beijing Institute of Technology（北京理工大学）；CNRS-UM LIRMM（法国国家科学研究中心-蒙彼利埃大学机器人与微电子实验室）
How to integrate human factors into the motion planning system is of great significance for improving the acceptance of intelligent vehicles. Decomposing motion into primitives and then accurately and smoothly joining the motion primitives (MPs) is an essential issue in the motion planning system. Therefore, the purpose of this paper is to regenerate and join the learned MPs in the library. By applying a representation algorithm based on the modified dynamic movement primitives (DMPs) and singular value decomposition (SVD), our method separates the basic shape parameters and fine-tuning shape …
This paper proposes a novel sampling-based motion planner, which integrates in RRT* (Rapidly exploring Random Tree star) a database of pre-computed motion primitives to alleviate its computational load and allow for motion planning in a dynamic or partially known environment. The database is built by considering a set of initial and final state pairs in some grid space, and determining for each pair an optimal trajectory that is compatible with the system dynamics and constraints, while minimizing a cost. Nodes are progressively added to the tree of feasible trajectories in the RRT* algorithm …
This paper presents Contact Mode Guided Manipulation Planning (CMGMP) for 3D quasistatic and quasidynamic rigid body motion planning in dexterous manipulation. The CMGMP algorithm generates hybrid motion plans including both continuous state transitions and discrete contact mode switches, without the need for pre-specified contact sequences or pre-designed motion primitives. The key idea is to use automatically enumerated contact modes of environment-object contacts to guide the tree expansions during the search. Contact modes automatically synthesize manipulation primitives, while the samplin…
Moscow Institute of Physics and Technology（莫斯科物理技术学院）；JSC Integrant（JSC Integrant公司）；Federal Research Center for Computer Science and Control RAS（俄罗斯科学院计算机科学与控制联邦研究中心）；AIRI
This paper addresses the kinodynamic motion planning for non-holonomic robots in dynamic environments with both static and dynamic obstacles -- a challenging problem that lacks a universal solution yet. One of the promising approaches to solve it is decomposing the problem into the smaller sub problems and combining the local solutions into the global one. The crux of any planning method for non-holonomic robots is the generation of motion primitives that generates solutions to local planning sub-problems. In this work we introduce a novel learnable steering function (policy), which takes into…
University of Lincoln（林肯大学）；Centre for Autonomous Systems (L-CAS)（自主系统中心（L-CAS））
Robotic technology is increasingly considered the major mean for fruit picking. However, picking fruits in a dense cluster imposes a challenging research question in terms of motion/path planning as conventional planning approaches may not find collision-free movements for the robot to reach-and-pick a ripe fruit within a dense cluster. In such cases, the robot needs to safely push unripe fruits to reach a ripe one. Nonetheless, existing approaches to planning pushing movements in cluttered environments either are computationally expensive or only deal with 2-D cases and are not suitable for f…
We present a method to apply heuristic search algorithms to solve rearrangement planning by pushing problems. In these problems, a robot must push an object through clutter to achieve a goal. To do this, we exploit the fact that contact with objects in the environment is critical to goal achievement. We dynamically generate goal-directed primitives that create and maintain contact between robot and object at each state expansion during the search. These primitives focus exploration toward critical areas of state-space, providing tractability to the high-dimensional planning problem. We demonst…
To solve the autonomous navigation problem in complex environments, an efficient motion planning approach is newly presented in this paper. Considering the challenges from large-scale, partially unknown complex environments, a three-layer motion planning framework is elaborately designed, including global path planning, local path optimization, and time-optimal velocity planning. Compared with existing approaches, the novelty of this work is twofold: 1) a novel heuristic-guided pruning strategy of motion primitives is proposed and fully integrated into the state lattice-based global path plann…
The objective of this work is to augment the basic abilities of a robot by learning to use sensorimotor primitives to solve complex long-horizon manipulation problems. This requires flexible generative planning that can combine primitive abilities in novel combinations and thus generalize across a wide variety of problems. In order to plan with primitive actions, we must have models of the actions: under what circumstances will executing this primitive successfully achieve some particular effect in the world? We use, and develop novel improvements on, state-of-the-art methods for active learni…
Integrated Task and Motion Planning (ITMP) for mobile robots in a dynamic environment with moving obstacles is a challenging research question and attracts more and more attentions recently. Most existing methods either restrict to static environments or lack performance guarantees. This motivates us to investigate the ITMP problem using formal methods and propose a bottom-up compositional design approach called CoSMoP (Composition of Safe Motion Primitives). Our basic idea is to synthesize a global motion plan through composing simple local moves and actions, and to achieve its performance gu…
The objective of this work is to augment the basic abilities of a robot by learning to use new sensorimotor primitives to enable the solution of complex long-horizon problems. Solving long-horizon problems in complex domains requires flexible generative planning that can combine primitive abilities in novel combinations to solve problems as they arise in the world. In order to plan to combine primitive actions, we must have models of the preconditions and effects of those actions: under what circumstances will executing this primitive achieve some particular effect in the world? We use, and de…
Robot manipulation in cluttered scenes often requires contact-rich interactions with objects. It can be more economical to interact via non-prehensile actions, for example, push through other objects to get to the desired grasp pose, instead of deliberate prehensile rearrangement of the scene. For each object in a scene, depending on its properties, the robot may or may not be allowed to make contact with, tilt, or topple it. To ensure that these constraints are satisfied during non-prehensile interactions, a planner can query a physics-based simulator to evaluate the complex multi-body intera…
