We gratefully acknowledge support from
the Simons Foundation
and member institutions


New submissions

[ total of 20 entries: 1-20 ]
[ showing up to 2000 entries per page: fewer | more ]

New submissions for Tue, 17 Jul 18

[1]  arXiv:1807.05211 [pdf, other]
Title: Learning Deployable Navigation Policies at Kilometer Scale from a Single Traversal
Subjects: Robotics (cs.RO)

Model-free reinforcement learning has recently been shown to be effective at learning navigation policies from complex image input. However, these algorithms tend to require large amounts of interaction with the environment, which can be prohibitively costly to obtain on robots in the real world. We present an approach for efficiently learning goal-directed navigation policies on a mobile robot, from only a single coverage traversal of recorded data. The navigation agent learns an effective policy over a diverse action space in a large heterogeneous environment consisting of more than 2km of travel, through buildings and outdoor regions that collectively exhibit large variations in visual appearance, self-similarity, and connectivity. We compare pretrained visual encoders that enable precomputation of visual embeddings to achieve a throughput of tens of thousands of transitions per second at training time on a commodity desktop computer, allowing agents to learn from millions of trajectories of experience in a matter of hours. We propose multiple forms of computationally efficient stochastic augmentation to enable the learned policy to generalise beyond these precomputed embeddings, and demonstrate successful deployment of the learned policy on the real robot without fine tuning, despite environmental appearance differences at test time. The dataset and code required to reproduce these results and apply the technique to other datasets and robots is made publicly available at rl-navigation.github.io/deployable.

[2]  arXiv:1807.05275 [pdf, other]
Title: LSTM-Based Zero-Velocity Detection for Robust Inertial Navigation
Comments: In Proceedings of the International Conference on Indoor Positioning and Indoor Navigation (IPIN'18), Nantes, France, Sep. 24-27, 2018
Subjects: Robotics (cs.RO); Human-Computer Interaction (cs.HC)

We present a method to improve the accuracy of a zero-velocity-aided inertial navigation system (INS) by replacing the standard zero-velocity detector with a long short-term memory (LSTM) neural network. While existing threshold-based zero-velocity detectors are not robust to varying motion types, our learned model accurately detects stationary periods of the inertial measurement unit (IMU) despite changes in the motion of the user. Upon detection, zero-velocity pseudo-measurements are fused with a dead reckoning motion model in an extended Kalman filter (EKF). We demonstrate that our LSTM-based zero-velocity detector, used within a zero-velocity-aided INS, improves zero-velocity detection during human localization tasks. Consequently, localization accuracy is also improved.
Our system is evaluated on more than 7.5 km of indoor pedestrian locomotion data, acquired from five different subjects. We show that 3D positioning error is reduced by over 34% compared to existing fixed-threshold zero-velocity detectors for walking, running, and stair climbing motions. Additionally, we demonstrate how our learned zero-velocity detector operates effectively during crawling and ladder climbing. Our system is calibration-free (no careful threshold-tuning is required) and operates consistently with differing users, IMU placements, and shoe types, while being compatible with any generic zero-velocity-aided INS.

[3]  arXiv:1807.05289 [pdf, other]
Title: Transfer Learning for High-Precision Trajectory Tracking Through $\mathcal{L}_1$ Adaptive Feedback and Iterative Learning
Subjects: Robotics (cs.RO); Systems and Control (cs.SY)

Robust and adaptive control strategies are needed when robots or automated systems are introduced to unknown and dynamic environments where they are required to cope with disturbances, unmodeled dynamics, and parametric uncertainties. In this paper, we demonstrate the capabilities of a combined $\mathcal{L}_1$ adaptive control and iterative learning control (ILC) framework to achieve high-precision trajectory tracking in the presence of unknown and changing disturbances. The $\mathcal{L}_1$ adaptive controller makes the system behave close to a reference model; however, it does not guarantee that perfect trajectory tracking is achieved, while ILC improves trajectory tracking performance based on previous iterations. The combined framework in this paper uses $\mathcal{L}_1$ adaptive control as an underlying controller that achieves a robust and repeatable behavior, while the ILC acts as a high-level adaptation scheme that mainly compensates for systematic tracking errors. We illustrate that this framework enables transfer learning between dynamically different systems, where learned experience of one system can be shown to be beneficial for another different system. Experimental results with two different quadrotors show the superior performance of the combined $\mathcal{L}_1$-ILC framework compared with approaches using ILC with an underlying proportional-derivative controller or proportional-integral-derivative controller. Results highlight that our $\mathcal{L}_1$-ILC framework can achieve high-precision trajectory tracking when unknown and changing disturbances are present and can achieve transfer of learned experience between dynamically different systems. Moreover, our approach is able to achieve precise trajectory tracking in the first attempt when the initial input is generated based on the reference model of the adaptive controller.

[4]  arXiv:1807.05290 [pdf, other]
Title: Adaptive Model Predictive Control for High-Accuracy Trajectory Tracking in Changing Conditions
Subjects: Robotics (cs.RO); Systems and Control (cs.SY)

Robots and automated systems are being introduced to unknown and dynamic environments where they are required to handle disturbances, unmodeled dynamics and parametric uncertainties. Robust and adaptive control strategies are required to achieve high performance in these dynamic environments. In this paper, we propose a novel adaptive model predictive controller (MPC) that combines a model predictive controller with an underlying $\mathcal{L}_1$ adaptive controller to improve trajectory tracking of a system subject to unknown and changing disturbances. The $\mathcal{L}_1$ adaptive controller forces the system to behave in a predefined way, as specified by a reference model. A higher-level MPC then uses this reference model to calculate the optimal input given a cost function while taking into account input constraints. We focus on experimental validation of the proposed approach and demonstrate its effectiveness in experiments on a quadrotor. We show that the proposed approach has a lower trajectory tracking error compared to non-predictive, adaptive approaches and a predictive, non-adaptive approach even when external wind disturbances are applied.

[5]  arXiv:1807.05352 [pdf]
Title: Path Planning of an Autonomous Mobile Robot in a Dynamic Environment using Modified Bat Swarm Optimization
Subjects: Robotics (cs.RO)

This paper outlines a modification on the Bat Algorithm (BA), a kind of swarm optimization algorithms with for the mobile robot navigation problem in a dynamic environment. The main objectives of this work are to obtain the collision-free, shortest, and safest path between starting point and end point assuming a dynamic environment with moving obstacles. A New modification on the frequency parameter of the standard BA has been proposed in this work, namely, the Modified Frequency Bat Algorithm (MFBA). The path planning problem for the mobile robot in a dynamic environment is carried out using the proposed MFBA. The path planning is achieved in two modes; the first mode is called path generation and is implemented using the MFBA, this mode is enabled when no obstacles near the mobile robot exist. When an obstacle close to the mobile robot is detected, the second mode, i.e., the obstacle avoidance (OA) is initiated. Simulation experiments have been conducted to check the validity and the efficiency of the suggested MFBA based path planning algorithm by comparing its performance with that of the standard BA. The simulation results showed that the MFBA outperforms the standard BA by planning a collision-free path with shorter, safer, and smoother than the path obtained by its BA counterpart.

[6]  arXiv:1807.05395 [pdf, other]
Title: A Control Architecture with Online Predictive Planning for Position and Torque Controlled Walking of Humanoid Robots
Comments: IROS 2018
Subjects: Robotics (cs.RO)

A common approach to the generation of walking patterns for humanoid robots consists in adopting a layered control architecture. This paper proposes an architecture composed of three nested control loops. The outer loop exploits a robot kinematic model to plan the footstep positions. In the mid layer, a predictive controller generates a Center of Mass trajectory according to the well-known table-cart model. Through a whole-body inverse kinematics algorithm, we can define joint references for position controlled walking. The outcomes of these two loops are then interpreted as inputs of a stack-of-task QP-based torque controller, which represents the inner loop of the presented control architecture. This resulting architecture allows the robot to walk also in torque control, guaranteeing higher level of compliance. Real world experiments have been carried on the humanoid robot iCub.

[7]  arXiv:1807.05424 [pdf, other]
Title: Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation
Comments: 7 pages, 4 figures, submitted to ROBIO 2018
Subjects: Robotics (cs.RO); Multiagent Systems (cs.MA)

This paper proposes a navigation algorithm ori- ented to multi-agent dynamic environment. The algorithm is expressed as a hierarchical framework which contains a Hidden Markov Model (HMM) and Deep Reinforcement Learning (DRL). For simplification, we term our method Hierarchical Navigation Reinforcement Network (HNRN). In high-level architecture, we train an HMM to evaluate agents environment in order to obtain a score. According to this score, adaptive control action will be chosen. While in low-level architecture, two sub-systems are introduced, one is a differential target-driven system, which aims at heading to the target, the other is collision avoidance DRL system, which is used for avoiding obstacles in the dynamic environment. The advantage of this hierarchical system is to decouple the target-driven and collision avoidance tasks, leading to a faster and easier model to be trained. As the experiments manifest, our algorithm has faster learning efficiency and a higher success rate than traditional Velocity Obstacle (VO) algorithms and hybrid DRL method.

[8]  arXiv:1807.05452 [pdf]
Title: GaGARoS: A Gaze Guided Assistive Robotic System for Daily-Living Activities
Subjects: Robotics (cs.RO); Human-Computer Interaction (cs.HC)

Patients suffering from tetraplegia or quadriplegia have limited body motion which prevents them from performing daily-living activities. We have developed GaGARoS, an assistive robotic system with an intuitive free-view gaze interface. The user's point of regard is estimated in 3D space while allowing free head movement, and is combined with object recognition and trajectory planning. This framework allows the user to interact with objects using fixations. Two operational modes have been implemented to cater for different eventualities. The automatic mode performs a pre-defined task associated with a gaze-selected object, while the manual mode allows gaze control of the robot's end-effector position on the user's frame of reference. User studies reported effortless operation in automatic mode. A manual pick and place task achieved a success rate of 100% on the users' first attempt.

[9]  arXiv:1807.05722 [pdf, other]
Title: Automatic generation of ground truth for the evaluation of obstacle detection and tracking techniques
Subjects: Robotics (cs.RO); Databases (cs.DB)

As automated vehicles are getting closer to becoming a reality, it will become mandatory to be able to characterise the performance of their obstacle detection systems. This validation process requires large amounts of ground-truth data, which is currently generated by manually annotation. In this paper, we propose a novel methodology to generate ground-truth kinematics datasets for specific objects in real-world scenes. Our procedure requires no annotation whatsoever, human intervention being limited to sensors calibration. We present the recording platform which was exploited to acquire the reference data and a detailed and thorough analytical study of the propagation of errors in our procedure. This allows us to provide detailed precision metrics for each and every data item in our datasets. Finally some visualisations of the acquired data are given.

[10]  arXiv:1807.05924 [pdf]
Title: Bipedal Walking Robot using Deep Deterministic Policy Gradient
Comments: 10 pages, 8 pages
Subjects: Robotics (cs.RO); Artificial Intelligence (cs.AI); Machine Learning (cs.LG)

Machine learning algorithms have found several applications in the field of robotics and control systems. The control systems community has started to show interest towards several machine learning algorithms from the sub-domains such as supervised learning, imitation learning and reinforcement learning to achieve autonomous control and intelligent decision making. Amongst many complex control problems, stable bipedal walking has been the most challenging problem. In this paper, we present an architecture to design and simulate a planar bipedal walking robot(BWR) using a realistic robotics simulator, Gazebo. The robot demonstrates successful walking behaviour by learning through several of its trial and errors, without any prior knowledge of itself or the world dynamics. The autonomous walking of the BWR is achieved using reinforcement learning algorithm called Deep Deterministic Policy Gradient(DDPG). DDPG is one of the algorithms for learning controls in continuous action spaces. After training the model in simulation, it was observed that, with a proper shaped reward function, the robot achieved faster walking or even rendered a running gait with an average speed of 0.83 m/s. The gait pattern of the bipedal walker was compared with the actual human walking pattern. The results show that the bipedal walking pattern had similar characteristics to that of a human walking pattern.

Cross-lists for Tue, 17 Jul 18

[11]  arXiv:1807.04414 (cross-list from math.OC) [pdf, other]
Title: Maximizing Road Capacity Using Cars that Influence People
Subjects: Optimization and Control (math.OC); Robotics (cs.RO)

The emerging technology enabling autonomy in vehicles has led to a variety of new problems in transportation networks. In particular, challenges exist in guaranteeing safety and optimizing traffic flow when the transportation network is under heterogeneous use: when cars of differing levels of autonomy co-exist on the same roads. Problems involving heterogeneous use of transportation networks have diverged into two major techniques: one leveraging only local interactions between cars benefiting the vehicles locally, and the other leveraging only global control techniques benefiting the traffic network. In this paper, we attempt to bridge the gap between these two paradigms. Our key insight is that the micro level interactions between the vehicles can in fact inform and affect the global behavior of the network, and vice versa. To this end, we utilize features of high levels of autonomy such as platooning to inform low-level controllers that incorporate the interaction between the vehicles. We will examine a high-level queuing framework to study the capacity of a transportation network, and then outline a lower-level control framework that leverages local interactions between cars to achieve a more efficient traffic flow via intelligent reordering of the cars. Such reorderings can be enforced by leveraging the interaction between autonomous and human-driven cars. We present a novel algorithm to show that the local actions of the autonomous cars on the road can initiate optimal orderings for the global properties in spite of randomly allocated initial ordering of the vehicles. We showcase our algorithm using a simulated mixed-autonomy traffic network, where we illustrate the re-ordering in action.

[12]  arXiv:1807.05428 (cross-list from cs.CG) [pdf, other]
Title: Motion Planning for Multiple Unit-Ball Robots in $\mathbb{R}^d$
Subjects: Computational Geometry (cs.CG); Robotics (cs.RO)

We present a decoupled algorithm for motion planning for a collection of unit-balls moving among polyhedral obstacles in $\mathbb{R}^d$, for any $d \ge 2$. We assume that the robots have revolving areas in the vicinity of their start and target positions: Revolving areas are regions where robots can maneuver in order to give way to another moving robot. Given that this assumption is fulfilled, the algorithm is complete, namely it is guaranteed to find a solution or report that none exists. A key goal in our design is to make the revolving areas as economical as possible and in particular to allow different revolving areas to overlap. This makes the analysis rather involved but in return makes the algorithm conceptually fairly simple. We show that for the case of $m$ unit-discs moving among polygonal obstacles of total complexity $n$ in $\mathbb{R}^2$, the algorithm can be executed in $O(n^2m + m(m+n)\log(m+n))$ time. We implemented the algorithm for this case and tested it on several scenarios, for which we show experimental results for up to $1000$ robots. Finally, we address the problem of choosing the order of execution of the paths in decoupled algorithms that locally solve interferences and show that finding the optimal order of execution is NP-hard. This motivated us to develop a heuristic for choosing the order; we describe the heuristic and demonstrate its effectiveness in certain scenarios.

[13]  arXiv:1807.05597 (cross-list from cs.LG) [pdf, other]
Title: Deep Learning for Semantic Segmentation on Minimal Hardware
Comments: 12 pages, 5 figures, RoboCup International Symposium 2018
Subjects: Machine Learning (cs.LG); Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO); Machine Learning (stat.ML)

Deep learning has revolutionised many fields, but it is still challenging to transfer its success to small mobile robots with minimal hardware. Specifically, some work has been done to this effect in the RoboCup humanoid football domain, but results that are performant and efficient and still generally applicable outside of this domain are lacking. We propose an approach conceptually different from those taken previously. It is based on semantic segmentation and does achieve these desired properties. In detail, it is being able to process full VGA images in real-time on a low-power mobile processor. It can further handle multiple image dimensions without retraining, it does not require specific domain knowledge for achieving a high frame rate and it is applicable on a minimal mobile hardware.

Replacements for Tue, 17 Jul 18

[14]  arXiv:1707.01152 (replaced) [pdf, other]
Title: Improving Foot-Mounted Inertial Navigation Through Real-Time Motion Classification
Comments: In Proceedings of the International Conference on Indoor Positioning and Indoor Navigation (IPIN'17), Sapporo, Japan, Sep. 18-21, 2017
Subjects: Robotics (cs.RO); Human-Computer Interaction (cs.HC)
[15]  arXiv:1707.05301 (replaced) [pdf, other]
Title: Cheap or Robust? The Practical Realization of Self-Driving Wheelchair Technology
Comments: In Proceedings of the IEEE International Conference on Rehabilitation Robotics (ICORR'17), London, United Kingdom, Jul. 17-20, 2017
Subjects: Robotics (cs.RO)
[16]  arXiv:1707.08680 (replaced) [pdf, other]
Title: Entropy-Based $Sim(3)$ Calibration of 2D Lidars to Egomotion Sensors
Comments: In Proceedings of the IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI'16), Baden-Baden, Germany, Sep. 19-21, 2016. Best Student Paper Award
Subjects: Robotics (cs.RO)
[17]  arXiv:1805.05451 (replaced) [pdf, other]
Title: Overcoming the Challenges of Solar Rover Autonomy: Enabling Long-Duration Planetary Navigation
Comments: In Proceedings of the International Symposium on Artificial Intelligence, Robotics and Automation in Space (i-SAIRAS'18), Madrid, Spain, Jun, 4-6, 2018
Subjects: Robotics (cs.RO)
[18]  arXiv:1801.04134 (replaced) [pdf, other]
Title: Deep Episodic Memory: Encoding, Recalling, and Predicting Episodic Experiences for Robot Action Execution
Subjects: Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
[19]  arXiv:1802.03515 (replaced) [pdf, other]
Title: Vehicle Pose and Shape Estimation through Multiple Monocular Vision
Comments: 8 pages, 8 figures
Subjects: Computer Vision and Pattern Recognition (cs.CV); Robotics (cs.RO)
[20]  arXiv:1805.11996 (replaced) [pdf, ps, other]
Title: Robotics and Integrated Formal Methods: Necessity meets Opportunity
Comments: 10 Pages, accepted at iFM2018
Subjects: Software Engineering (cs.SE); Robotics (cs.RO)
[ total of 20 entries: 1-20 ]
[ showing up to 2000 entries per page: fewer | more ]

Disable MathJax (What is MathJax?)