arXiv subjects

Jun Luo

Publications and source records attributed to Jun Luo.

At least 199 records · Page 11Linked to original sources

arXiv2021

Affordance as general value function: A computational model

General value functions (GVFs) in the reinforcement learning (RL) literature are long-term predictive summaries of the outcomes of agents following specific policies in the environment. Affordances as perceived action possibilities with specific valence may be cast into predicted policy-relative goodness and modelled as GVFs. A systematic explication of this connection shows that GVFs and especially their deep learning embodiments (1) realize affordance prediction as a form of direct perception, (2) illuminate the fundamental connection between action and perception in affordance, and (3) offer a scalable way to learn affordances using RL methods. Through an extensive review of existing literature on GVF applications and representative affordance research in robotics, we demonstrate that GVFs provide the right framework for learning affordances in real-world applications. In addition, we highlight a few new avenues of research opened up by the perspective of "affordance as GVF", including using GVFs for orchestrating complex behaviors.

cs.AI↗

arXiv2021

On Lambda Function and a Quantification of Torhorst Theorem

To any compact $K\subset\hat{\mathbb{C}}$ we associate a map $λ_K: \hat{\mathbb{C}}\rightarrow\mathbb{N}\cup\{\infty\}$ -- the lambda function of $K$ -- such that a planar continuum $K$ is locally connected if and only if $Λ_K(x)\equiv0$. We establish basic methods of determining the lambda function $λ_K$ for specific compacta $K\subset\hat{\mathbb{C}}$, including a gluing lemma for lambda functions and some inequalities. One of these inequalities comes from an interplay between the topological difficulty of a planar compactum $K$ and that of a sub-compactum $L\subset K$, lying on the boundary of a component of $\hat{\mathbb{C}}\setminus K$. It generalizes and quantifies the result of Torhorst Theorem, a fundamental result from plane topology. We also find three conditions under which this inequality is actually an equality. Under one of these conditions, this equality provides a quantitative version for Whyburn's Theorem, which is a partial converse to Torhorst Theorem.

math.GN↗

arXiv2021

PURE: Passive mUlti-peRson idEntification via Deep Footstep Separation and Recognition

Recently, \textit{passive behavioral biometrics} (e.g., gesture or footstep) have become promising complements to conventional user identification methods (e.g., face or fingerprint) under special situations, yet existing sensing technologies require lengthy measurement traces and cannot identify multiple users at the same time. To this end, we propose \systemname\ as a passive multi-person identification system leveraging deep learning enabled footstep separation and recognition. \systemname\ passively identifies a user by deciphering the unique "footprints" in its footstep. Different from existing gait-enabled recognition systems incurring a long sensing delay to acquire many footsteps, \systemname\ can recognize a person by as few as only one step, substantially cutting the identification latency. To make \systemname\ adaptive to walking pace variations, environmental dynamics, and even unseen targets, we apply an adversarial learning technique to improve its domain generalisability and identification accuracy. Finally, \systemname\ can defend itself against replay attack, enabled by the richness of footstep and spatial awareness. We implement a \systemname\ prototype using commodity hardware and evaluate it in typical indoor settings. Evaluation results demonstrate a cross-domain identification accuracy of over 90\%.

cs.CV↗

arXiv2021

Self-Supervised Simultaneous Multi-Step Prediction of Road Dynamics and Cost Map

While supervised learning is widely used for perception modules in conventional autonomous driving solutions, scalability is hindered by the huge amount of data labeling needed. In contrast, while end-to-end architectures do not require labeled data and are potentially more scalable, interpretability is sacrificed. We introduce a novel architecture that is trained in a fully self-supervised fashion for simultaneous multi-step prediction of space-time cost map and road dynamics. Our solution replaces the manually designed cost function for motion planning with a learned high dimensional cost map that is naturally interpretable and allows diverse contextual information to be integrated without manual data labeling. Experiments on real world driving data show that our solution leads to lower number of collisions and road violations in long planning horizons in comparison to baselines, demonstrating the feasibility of fully self-supervised prediction without sacrificing either scalability or interpretability.

cs.CV↗

arXiv2021

Graph-SIM: A Graph-based Spatiotemporal Interaction Modelling for Pedestrian Action Prediction

One of the most crucial yet challenging tasks for autonomous vehicles in urban environments is predicting the future behaviour of nearby pedestrians, especially at points of crossing. Predicting behaviour depends on many social and environmental factors, particularly interactions between road users. Capturing such interactions requires a global view of the scene and dynamics of the road users in three-dimensional space. This information, however, is missing from the current pedestrian behaviour benchmark datasets. Motivated by these challenges, we propose 1) a novel graph-based model for predicting pedestrian crossing action. Our method models pedestrians' interactions with nearby road users through clustering and relative importance weighting of interactions using features obtained from the bird's-eye-view. 2) We introduce a new dataset that provides 3D bounding box and pedestrian behavioural annotations for the existing nuScenes dataset. On the new data, our approach achieves state-of-the-art performance by improving on various metrics by more than 15% in comparison to existing methods. The dataset is available at https://github.com/huawei-noah/datasets/PePScenes.

cs.CV↗

arXiv2021

Learning robust driving policies without online exploration

We propose a multi-time-scale predictive representation learning method to efficiently learn robust driving policies in an offline manner that generalize well to novel road geometries, and damaged and distracting lane conditions which are not covered in the offline training data. We show that our proposed representation learning method can be applied easily in an offline (batch) reinforcement learning setting demonstrating the ability to generalize well and efficiently under novel conditions compared to standard batch RL methods. Our proposed method utilizes training data collected entirely offline in the real-world which removes the need of intensive online explorations that impede applying deep reinforcement learning on real-world robot training. Various experiments were conducted in both simulator and real-world scenarios for the purpose of evaluation and analysis of our proposed claims.

cs.RO↗

arXiv2021

Review on Ranking and Selection: A New Perspective

In this paper, we briefly review the development of ranking-and-selection (R&S) in the past 70 years, especially the theoretical achievements and practical applications in the last 20 years. Different from the frequentist and Bayesian classifications adopted by Kim and Nelson (2006b) and Chick (2006) in their review articles, we categorize existing R&S procedures into fixed-precision and fixed-budget procedures, as in Hunter and Nelson (2017). We show that these two categories of procedures essentially differ in the underlying methodological formulations, i.e., they are built on hypothesis testing and dynamic-programming, respectively. In light of this variation, we review in detail some well-known procedures in the literature and show how they fit into these two formulations. In addition, we discuss the use of R&S procedures in solving various practical problems and propose what we think are the important research questions in the field.

math.OC↗

arXiv2021

Open-set Intersection Intention Prediction for Autonomous Driving

Intention prediction is a crucial task for Autonomous Driving (AD). Due to the variety of size and layout of intersections, it is challenging to predict intention of human driver at different intersections, especially unseen and irregular intersections. In this paper, we formulate the prediction of intention at intersections as an open-set prediction problem that requires context specific matching of the target vehicle state and the diverse intersection configurations that are in principle unbounded. We capture map-centric features that correspond to intersection structures under a spatial-temporal graph representation, and use two MAAMs (mutually auxiliary attention module) that cover respectively lane-level and exitlevel intentions to predict a target that best matches intersection elements in map-centric feature space. Under our model, attention scores estimate the probability distribution of the openset intentions that are contextually defined by the structure of the current intersection. The proposed model is trained and evaluated on simulated dataset. Furthermore, the model, trained on simulated dataset and without any fine tuning, is directly validated on in-house real-world dataset collected at 98 realworld intersections and exhibits satisfactory performance,demonstrating the practical viability of our approach.

cs.RO↗

arXiv2021

Diverse Auto-Curriculum is Critical for Successful Real-World Multiagent Learning Systems

Multiagent reinforcement learning (MARL) has achieved a remarkable amount of success in solving various types of video games. A cornerstone of this success is the auto-curriculum framework, which shapes the learning process by continually creating new challenging tasks for agents to adapt to, thereby facilitating the acquisition of new skills. In order to extend MARL methods to real-world domains outside of video games, we envision in this blue sky paper that maintaining a diversity-aware auto-curriculum is critical for successful MARL applications. Specifically, we argue that \emph{behavioural diversity} is a pivotal, yet under-explored, component for real-world multiagent learning systems, and that significant work remains in understanding how to design a diversity-aware auto-curriculum. We list four open challenges for auto-curriculum techniques, which we believe deserve more attention from this community. Towards validating our vision, we recommend modelling realistic interactive behaviours in autonomous driving as an important test bed, and recommend the SMARTS/ULTRA benchmark.

cs.AI↗

arXiv2021

Effect of Earth-Moon's gravity on TianQin's range acceleration noise

TianQin is a proposed space gravitational-wave detection mission using circular high Earth orbits. The geocentric concept has raised questions about the disturbing effect of the nearby gravity field of the Earth-Moon system on the highly-sensitive intersatellite ranging measurements. Here we examine the issue through high precision numerical orbit simulation with detailed gravity-field models. By evaluating range accelerations between distant free-falling test masses, the study shows that the majority of the Earth-Moon's gravity disturbances are not in TianQin's detection frequency band above $10^{-4}$ Hz, and hence present no showstoppers to the mission.

gr-qc↗

arXiv2021

CoachNet: An Adversarial Sampling Approach for Reinforcement Learning

Despite the recent successes of reinforcement learning in games and robotics, it is yet to become broadly practical. Sample efficiency and unreliable performance in rare but challenging scenarios are two of the major obstacles. Drawing inspiration from the effectiveness of deliberate practice for achieving expert-level human performance, we propose a new adversarial sampling approach guided by a failure predictor named "CoachNet". CoachNet is trained online along with the agent to predict the probability of failure. This probability is then used in a stochastic sampling process to guide the agent to more challenging episodes. This way, instead of wasting time on scenarios that the agent has already mastered, training is focused on the agent's "weak spots". We present the design of CoachNet, explain its underlying principles, and empirically demonstrate its effectiveness in improving sample efficiency and test-time robustness in common continuous control tasks.

cs.LG↗

arXiv2020

LISPR: An Options Framework for Policy Reuse with Reinforcement Learning

We propose a framework for transferring any existing policy from a potentially unknown source MDP to a target MDP. This framework (1) enables reuse in the target domain of any form of source policy, including classical controllers, heuristic policies, or deep neural network-based policies, (2) attains optimality under suitable theoretical conditions, and (3) guarantees improvement over the source policy in the target MDP. These are achieved by packaging the source policy as a black-box option in the target MDP and providing a theoretically grounded way to learn the option's initiation set through general value functions. Our approach facilitates the learning of new policies by (1) maximizing the target MDP reward with the help of the black-box option, and (2) returning the agent to states in the learned initiation set of the black-box option where it is already optimal. We show that these two variants are equivalent in performance under some conditions. Through a series of experiments in simulated environments, we demonstrate that our framework performs excellently in sparse reward problems given (sub-)optimal source policies and improves upon prior art in transfer methods such as continual learning and progressive networks, which lack our framework's desirable theoretical properties.

cs.LG↗

arXiv2020

Prediction by Anticipation: An Action-Conditional Prediction Method based on Interaction Learning

In autonomous driving (AD), accurately predicting changes in the environment can effectively improve safety and comfort. Due to complex interactions among traffic participants, however, it is very hard to achieve accurate prediction for a long horizon. To address this challenge, we propose prediction by anticipation, which views interaction in terms of a latent probabilistic generative process wherein some vehicles move partly in response to the anticipated motion of other vehicles. Under this view, consecutive data frames can be factorized into sequential samples from an action-conditional distribution that effectively generalizes to a wider range of actions and driving situations. Our proposed prediction model, variational Bayesian in nature, is trained to maximize the evidence lower bound (ELBO) of the log-likelihood of this conditional distribution. Evaluations of our approach with prominent AD datasets NGSIM I-80 and Argoverse show significant improvement over current state-of-the-art in both accuracy and generalization.

cs.LG↗

arXiv2020

PePScenes: A Novel Dataset and Baseline for Pedestrian Action Prediction in 3D

Predicting the behavior of road users, particularly pedestrians, is vital for safe motion planning in the context of autonomous driving systems. Traditionally, pedestrian behavior prediction has been realized in terms of forecasting future trajectories. However, recent evidence suggests that predicting higher-level actions, such as crossing the road, can help improve trajectory forecasting and planning tasks accordingly. There are a number of existing datasets that cater to the development of pedestrian action prediction algorithms, however, they lack certain characteristics, such as bird's eye view semantic map information, 3D locations of objects in the scene, etc., which are crucial in the autonomous driving context. To this end, we propose a new pedestrian action prediction dataset created by adding per-frame 2D/3D bounding box and behavioral annotations to the popular autonomous driving dataset, nuScenes. In addition, we propose a hybrid neural network architecture that incorporates various data modalities for predicting pedestrian crossing action. By evaluating our model on the newly proposed dataset, the contribution of different data modalities to the prediction task is revealed. The dataset is available at https://github.com/huawei-noah/PePScenes.

cs.CV↗

arXiv2020

Optimizing orbits for TianQin

TianQin is a geocentric space-based gravitational-wave observatory mission consisting of three drag-free controlled satellites in an equilateral triangle with an orbital radius of $ 10^{5}$ km. The constellation faces the white-dwarf binary RX J0806.3+1527 located slightly below the ecliptic plane, and is subject to gravitational perturbations that can distort the formation. In this study, we present combined methods to optimize the TianQin orbits so that a set of 5-year stability requirements can be met. Moreover, we discuss slow long-term drift of the detector pointing due to orbital precession, and put forward stable orbits with six other pointings along the lunar orbital plane. Some implications of the findings are pointed out.

gr-qc↗

arXiv2020

Multi-Modal Hybrid Architecture for Pedestrian Action Prediction

Pedestrian behavior prediction is one of the major challenges for intelligent driving systems in urban environments. Pedestrians often exhibit a wide range of behaviors and adequate interpretations of those depend on various sources of information such as pedestrian appearance, states of other road users, the environment layout, etc. To address this problem, we propose a novel multi-modal prediction algorithm that incorporates different sources of information captured from the environment to predict future crossing actions of pedestrians. The proposed model benefits from a hybrid learning architecture consisting of feedforward and recurrent networks for analyzing visual features of the environment and dynamics of the scene. Using the existing 2D pedestrian behavior benchmarks and a newly annotated 3D driving dataset, we show that our proposed model achieves state-of-the-art performance in pedestrian crossing prediction.

cs.CV↗

arXiv2020

SMARTS: Scalable Multi-Agent Reinforcement Learning Training School for Autonomous Driving

Multi-agent interaction is a fundamental aspect of autonomous driving in the real world. Despite more than a decade of research and development, the problem of how to competently interact with diverse road users in diverse scenarios remains largely unsolved. Learning methods have much to offer towards solving this problem. But they require a realistic multi-agent simulator that generates diverse and competent driving interactions. To meet this need, we develop a dedicated simulation platform called SMARTS (Scalable Multi-Agent RL Training School). SMARTS supports the training, accumulation, and use of diverse behavior models of road users. These are in turn used to create increasingly more realistic and diverse interactions that enable deeper and broader research on multi-agent interaction. In this paper, we describe the design goals of SMARTS, explain its basic architecture and its key features, and illustrate its use through concrete multi-agent experiments on interactive scenarios. We open-source the SMARTS platform and the associated benchmark tasks and evaluation metrics to encourage and empower research on multi-agent learning for autonomous driving. Our code is available at https://github.com/huawei-noah/SMARTS.

cs.MA↗

arXiv2020

No Perfect Outdoors: Towards A Deep Profiling of GNSS-based Location Contexts

While both outdoor and indoor localization methods are flourishing, how to properly marry them to offer pervasive localizability in urban areas remains open. Recently proposals on indoor-outdoor detection make the first step towards such an integration, yet complicated urban environments render such a binary classification incompetent. In this paper, we intend to fully explore raw GNSS measurements in order to better characterize the diversified urban environments. Essentially, we tackle the challenges introduced by the complex GNSS data and apply a deep learning model to identify representations for respective location contexts. We further develop two preliminary applications of our deep profiling. On one hand, we offer a more fine-grained semantic classification than binary indoor-outdoor detection. On the other hand, we derive a GPS error indicator more meaningful than that provided by Google Maps. These results are all corroborated by our extensive data collection and trace-driven evaluations.

cs.NI↗