Despite recent progress in robot learning, it still remains a challenge to program a robot to deal with open-ended object manipulation tasks. One approach that was recently used to autonomously generate a repertoire of diverse skills is a novelty based Quality-Diversity~(QD) algorithm. However, as most evolutionary algorithms, QD suffers from sample-inefficiency and, thus, it is challenging to apply it in real-world scenarios. This paper tackles this problem by integrating a neural network that predicts the behavior of the perturbed parameters into a novelty based QD algorithm. In the proposed Model-based Quality-Diversity search (M-QD), the network is trained concurrently to the repertoire and is used to avoid executing unpromising actions in the novelty search process. Furthermore, it is used to adapt the skills of the final repertoire in order to generalize the skills to different scenarios. Our experiments show that enhancing a QD algorithm with such a forward model improves the sample-efficiency and performance of the evolutionary process and the skill adaptation.
Imperial College London（帝国理工学院）；University of Patras（帕特雷大学）
In real-world environments, robots need to be resilient to damages and robust to unforeseen scenarios. Quality-Diversity (QD) algorithms have been successfully used to make robots adapt to damages in seconds by leveraging a diverse set of learned skills. A high diversity of skills increases the chances of a robot to succeed at overcoming new situations since there are more potential alternatives to solve a new task.However, finding and storing a large behavioural diversity of multiple skills often leads to an increase in computational complexity. Furthermore, robot planning in a large skill sp…
The article introduces the concept of "diversity-aware" robotics and discusses the need to develop computational models to embed robots with diversity-awareness: that is, robots capable of adapting and re-configuring their behavior to recognize, respect, and value the uniqueness of the person they interact with to promote inclusion regardless of their age, race, gender, cognitive or physical capabilities, etc. Finally, the article discusses possible technical solutions based on Ontologies and Bayesian Networks, starting from previous experience with culturally competent robots.
air4children: Artificial Intelligence and Robotics for Children（air4children：儿童人工智能与机器人项目）
In this paper, we present preliminary work from a pilot workshop that aimed to promote diversity and inclusion for fundamentals of Artificial Intelligence and Robotics for Children (air4children) in the context of developing countries. Considering the scarcity of funding and the little to none availability of specialised professionals to teach AI and robotics in developing countries, we present resources based on free open-source hardware and software, open educational resources, and alternative education programs. That said, the contribution of this work is the pilot workshop of four lessons …
Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
National University of Singapore（新加坡国立大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））；Institude for Information Research, A STAR（A*STAR信息研究所）
University of Southern California（南加州大学）；Google Brain（谷歌大脑）
In principle, reinforcement learning and policy search methods can enable robots to learn highly complex and general skills that may allow them to function amid the complexity and diversity of the real world. However, training a policy that generalizes well across a wide range of real-world conditions requires far greater quantity and diversity of experience than is practical to collect with a single robot. Fortunately, it is possible for multiple robots to share their experience with one another, and thereby, learn a policy collectively. In this work, we explore distributed and asynchronous p…
Red-Teaming Vision-Language-Action Models via Quality Diversity Prompt Generation for Robust Robot Policies
Thomas Lord Department of Computer Science, University of Southern California（南加州大学托马斯·洛德计算机科学系）；Sony AI（索尼AI）；Sibley School of Mechanical and Aerospace Engineering, Cornell University（康奈尔大学西布利机械与航空航天工程学院）
Mobile soft robots offer compelling applications in fields ranging from urban search and rescue to planetary exploration. A critical challenge of soft robotic control is that the nonlinear dynamics imposed by soft materials often result in complex behaviors that are counterintuitive and hard to model or predict. As a consequence, most behaviors for mobile soft robots are discovered through empirical trial and error and hand-tuning. A second challenge is that soft materials are difficult to simulate with high fidelity -- leading to a significant reality gap when trying to discover or optimize n…
In this paper, we study the symmetric rendezvous search problem on the line with n > 2 robots that are unaware of their locations and the initial distances between them. In the symmetric version of this problem, the robots execute the same strategy. The multi-robot symmetric rendezvous algorithm, MSR presented in this paper is an extension our symmetric rendezvous algorithm, SR presented in [23]. We study both the synchronous and asynchronous cases of the problem. The asynchronous version of MSR algorithm is called MASR algorithm. We consider that robots start executing MASR at different times…
Imperial College London（伦敦帝国理工学院）；University of Patras（帕特雷大学）
Adaptation capabilities, like damage recovery, are crucial for the deployment of robots in complex environments. Several works have demonstrated that using repertoires of pre-trained skills can enable robots to adapt to unforeseen mechanical damages in a few minutes. These adaptation capabilities are directly linked to the behavioural diversity in the repertoire. The more alternatives the robot has to execute a skill, the better are the chances that it can adapt to a new situation. However, solving complex tasks, like maze navigation, usually requires multiple different skills. Finding a large…
Quality-Diversity algorithms refer to a class of evolutionary algorithms designed to find a collection of diverse and high-performing solutions to a given problem. In robotics, such algorithms can be used for generating a collection of controllers covering most of the possible behaviours of a robot. To do so, these algorithms associate a behavioural descriptor to each of these behaviours. Each behavioural descriptor is used for estimating the novelty of one behaviour compared to the others. In most existing algorithms, the behavioural descriptor needs to be hand-coded, thus requiring prior kno…
We present a Quality-Diversity benchmark suite for Deep Neuroevolution in Reinforcement Learning domains for robot control. The suite includes the definition of tasks, environments, behavioral descriptors, and fitness. We specify different benchmarks based on the complexity of both the task and the agent controlled by a deep neural network. The benchmark uses standard Quality-Diversity metrics, including coverage, QD-score, maximum fitness, and an archive profile metric to quantify the relation between coverage and fitness. We also present how to quantify the robustness of the solutions with r…
Quality-Diversity algorithms provide efficient mechanisms to generate large collections of diverse and high-performing solutions, which have shown to be instrumental for solving downstream tasks. However, most of those algorithms rely on a behavioural descriptor to characterise the diversity that is hand-coded, hence requiring prior knowledge about the considered tasks. In this work, we introduce Relevance-guided Unsupervised Discovery of Abilities; a Quality-Diversity algorithm that autonomously finds a behavioural characterisation tailored to the task at hand. In particular, our method intro…
Improving open-ended learning capabilities is a promising approach to enable robots to face the unbounded complexity of the real-world. Among existing methods, the ability of Quality-Diversity algorithms to generate large collections of diverse and high-performing skills is instrumental in this context. However, most of those algorithms rely on a hand-coded behavioural descriptor to characterise the diversity, hence requiring prior knowledge about the considered tasks. In this work, we propose an additional analysis of Autonomous Robots Realising their Abilities; a Quality-Diversity algorithm …
Reinforcement learning agents need a reward signal to learn successful policies. When this signal is sparse or the corresponding gradient is deceptive, such agents need a dedicated mechanism to efficiently explore their search space without relying on the reward. Looking for a large diversity of behaviors or using Motion Planning (MP) algorithms are two options in this context. In this paper, we build on the common roots between these two options to investigate the properties of two diversity search algorithms, the Novelty Search and the Goal Exploration Process algorithms. These algorithms lo…
Quality-Diversity (QD) algorithms are powerful exploration algorithms that allow robots to discover large repertoires of diverse and high-performing skills. However, QD algorithms are sample inefficient and require millions of evaluations. In this paper, we propose Dynamics-Aware Quality-Diversity (DA-QD), a framework to improve the sample efficiency of QD algorithms through the use of dynamics models. We also show how DA-QD can then be used for continual acquisition of new skill repertoires. To do so, we incrementally train a deep dynamics model from experience obtained when performing skill …
School of Computing, Informatics, and Decision Systems Engineering, Arizona State University（亚利桑那州立大学计算、信息与决策系统工程学院）
Despite the significant success at enabling robots with autonomous behaviors makes deep reinforcement learning a promising approach for robotic object search task, the deep reinforcement learning approach severely suffers from the nature sparse reward setting of the task. To tackle this challenge, we present a novel policy learning paradigm for the object search task, based on hierarchical and interpretable modeling with an intrinsic-extrinsic reward setting. More specifically, we explore the environment efficiently through a proxy low-level policy which is driven by the intrinsic rewarding su…
The optimization of functions to find the best solution according to one or several objectives has a central role in many engineering and research fields. Recently, a new family of optimization algorithms, named Quality-Diversity optimization, has been introduced, and contrasts with classic algorithms. Instead of searching for a single solution, Quality-Diversity algorithms are searching for a large collection of both diverse and high-performing solutions. The role of this collection is to cover the range of possible solution types as much as possible, and to contain the best solution for each…
Visual search of relevant targets in the environment is a crucial robot skill. We propose a preliminary framework for the execution monitor of a robot task, taking care of the robot attitude to visually searching the environment for targets involved in the task. Visual search is also relevant to recover from a failure. The framework exploits deep reinforcement learning to acquire a "common sense" scene structure and it takes advantage of a deep convolutional network to detect objects and relevant relations holding between them. The framework builds on these methods to introduce a vision-based …
In this work, we consider the problem of Quality-Diversity (QD) optimization with multiple objectives. QD algorithms have been proposed to search for a large collection of both diverse and high-performing solutions instead of a single set of local optima. Thriving for diversity was shown to be useful in many industrial and robotics applications. On the other hand, most real-life problems exhibit several potentially antagonist objectives to be optimized. Hence being able to optimize for multiple objectives with an appropriate technique while thriving for diversity is important to many fields. H…
We propose an evolutionary computation method for an adversarial attack on the length and thickness of parts of legged robots by deep reinforcement learning. This attack changes the robot body shape and interferes with walking-we call the attacked body as adversarial body shape. The evolutionary computation method searches adversarial body shape by minimizing the expected cumulative reward earned through walking simulation. To evaluate the effectiveness of the proposed method, we perform experiments with three-legged robots, Walker2d, Ant-v2, and Humanoid-v2 in OpenAI Gym. The experimental res…
University of Oxford（牛津大学）；Huawei Noah’s Ark Lab（华为诺亚方舟实验室）
Searching for the architecture cells is a dominant paradigm in NAS. However, little attention has been devoted to the analysis of the cell-based search spaces even though it is highly important for the continual development of NAS. In this work, we conduct an empirical post-hoc analysis of architectures from the popular cell-based search spaces and find that the existing search spaces contain a high degree of redundancy: the architecture performance is minimally sensitive to changes at large parts of the cells, and universally adopted designs, like the explicit search for a reduction cell, sig…
Indian Institute of Technology Madras（印度理工学院马德拉斯分校）；Microsoft（微软）
Retrieving keywords (bidwords) with the same intent as query, referred to as close variant keywords, is of prime importance for effective targeted search advertising. For head and torso search queries, sponsored search engines use a huge repository of same intent queries and keywords, mined ahead of time. Online, this repository is used to rewrite the query and then lookup the rewrite in a repository of bid keywords contributing to significant revenue. Recently generative retrieval models have been shown to be effective at the task of generating such query rewrites. We observe two main limitat…
