Planning Multimodal Exploratory Actions for Online Robot Attribute Learning

Robots frequently need to perceive object attributes, such as "red," "heavy," and "empty," using multimodal exploratory actions, such as "look," "lift," and "shake." Robot attribute learning algorithms aim to learn an observation model for each perceivable attribute given an exploratory action. Once the attribute models are learned, they can be used to identify attributes of new objects, answering questions, such as "Is this object red and empty?" Attribute learning and identification are being treated as two separate problems in the literature. In this paper, we first define a new problem called online robot attribute learning (On-RAL), where the robot works on attribute learning and attribute identification simultaneously. Then we develop an algorithm called information-theoretic reward shaping (ITRS) that actively addresses the trade-off between exploration and exploitation in On-RAL problems. ITRS was compared with competitive robot attribute learning baselines, and experimental results demonstrate ITRS' superiority in learning efficiency and identification accuracy.

Effective and Scalable Clustering on Massive Attributed Graphs

Given a graph G where each node is associated with a set of attributes, and a parameter k specifying the number of output clusters, k-attributed graph clustering (k-AGC) groups nodes in G into k disjoint clusters, such that nodes within the same cluster share similar topological and attribute characteristics, while those in different clusters are dissimilar. This problem is challenging on massive graphs, e.g., with millions of nodes and billions of edges. For such graphs, existing solutions either incur prohibitively high costs, or produce clustering results with compromised quality. In this paper, we propose ACMin, an effective approach to k-AGC that yields high-quality clusters with cost linear to the size of the input graph G. The main contributions of ACMin are twofold: (i) a novel formulation of the k-AGC problem based on an attributed multi-hop conductance quality measure custom-made for this problem setting, which effectively captures cluster coherence in terms of both topological proximities and attribute similarities, and (ii) a linear-time optimization solver that obtains high-quality clusters iteratively, based on efficient matrix operations such as orthogonal iterations, an alternative optimization approach, as well as an initialization technique that significantly speeds up the convergence of ACMin in practice. Extensive experiments, comparing 11 competitors on 6 real datasets, demonstrate that ACMin consistently outperforms all competitors in terms of result quality measured against ground-truth labels, while being up to orders of magnitude faster. In particular, on the Microsoft Academic Knowledge Graph dataset with 265.2 million edges and 1.1 billion attribute values, ACMin outputs high-quality results for 5-AGC within 1.68 hours using a single CPU core, while none of the 11 competitors finish within 3 days.

A Survey of Knowledge-based Sequential Decision Making under Uncertainty

Reasoning with declarative knowledge (RDK) and sequential decision-making (SDM) are two key research areas in artificial intelligence. RDK methods reason with declarative domain knowledge, including commonsense knowledge, that is either provided a priori or acquired over time, while SDM methods (probabilistic planning and reinforcement learning) seek to compute action policies that maximize the expected cumulative utility over a time horizon; both classes of methods reason in the presence of uncertainty. Despite the rich literature in these two areas, researchers have not fully explored their complementary strengths. In this paper, we survey algorithms that leverage RDK methods while making sequential decisions under uncertainty. We discuss significant developments, open problems, and directions for future work.

Learning and Reasoning for Robot Dialog and Navigation Tasks

Reinforcement learning and probabilistic reasoning algorithms aim at learning from interaction experiences and reasoning with probabilistic contextual knowledge respectively. In this research, we develop algorithms for robot task completions, while looking into the complementary strengths of reinforcement learning and probabilistic reasoning techniques. The robots learn from trial-and-error experiences to augment their declarative knowledge base, and the augmented knowledge can be used for speeding up the learning process in potentially different tasks. We have implemented and evaluated the developed algorithms using mobile robots conducting dialog and navigation tasks. From the results, we see that our robot's performance can be improved by both reasoning with human knowledge and learning from task-completion experience. More interestingly, the robot was able to learn from navigation tasks to improve its dialog strategies.

Adaptive Dialog Policy Learning with Hindsight and User Modeling

Reinforcement learning methods have been used to compute dialog policies from language-based interaction experiences. Efficiency is of particular importance in dialog policy learning, because of the considerable cost of interacting with people, and the very poor user experience from low-quality conversations. Aiming at improving the efficiency of dialog policy learning, we develop algorithm LHUA (Learning with Hindsight, User modeling, and Adaptation) that, for the first time, enables dialog agents to adaptively learn with hindsight from both simulated and real users. Simulation and hindsight provide the dialog agent with more experience and more (positive) reinforcements respectively. Experimental results suggest that, in success rate and policy quality, LHUA outperforms competitive baselines from the literature, including its no-simulation, no-adaptation, and no-hindsight counterparts.

Guided Dyna-Q for Mobile Robot Exploration and Navigation

Model-based reinforcement learning (RL) enables an agent to learn world models from trial-and-error experiences toward achieving long-term goals. Automated planning, on the other hand, can be used for accomplishing tasks through reasoning with declarative action knowledge. Despite their shared goal of completing complex tasks, the development of RL and automated planning has mainly been isolated due to their different modalities of computation. Focusing on improving model-based RL agent's exploration strategy and sample efficiency, we develop Guided Dyna-Q (GDQ) to enable RL agents to reason with action knowledge to avoid exploring less-relevant states toward more efficient task accomplishment. GDQ has been evaluated in simulation and using a mobile robot conducting navigation tasks in an office environment. Results show that GDQ reduces the effort in exploration while improving the quality of learned policies.

AutoEG: Automated Experience Grafting for Off-Policy Deep Reinforcement Learning

Deep reinforcement learning (RL) algorithms frequently require prohibitive interaction experience to ensure the quality of learned policies. The limitation is partly because the agent cannot learn much from the many low-quality trials in early learning phase, which results in low learning rate. Focusing on addressing this limitation, this paper makes a twofold contribution. First, we develop an algorithm, called Experience Grafting (EG), to enable RL agents to reorganize segments of the few high-quality trajectories from the experience pool to generate many synthetic trajectories while retaining the quality. Second, building on EG, we further develop an AutoEG agent that automatically learns to adjust the grafting-based learning strategy. Results collected from a set of six robotic control environments show that, in comparison to a standard deep RL algorithm (DDPG), AutoEG increases the speed of learning process by at least 30%.

iCORPP: Interleaved Commonsense Reasoning and Probabilistic Planning on Robots

Robot sequential decision-making in the real world is a challenge because it requires the robots to simultaneously reason about the current world state and dynamics, while planning actions to accomplish complex tasks. On the one hand, declarative languages and reasoning algorithms well support representing and reasoning with commonsense knowledge. But these algorithms are not good at planning actions toward maximizing cumulative reward over a long, unspecified horizon. On the other hand, probabilistic planning frameworks, such as Markov decision processes (MDPs) and partially observable MDPs (POMDPs), well support planning to achieve long-term goals under uncertainty. But they are ill-equipped to represent or reason about knowledge that is not directly related to actions. In this article, we present a novel algorithm, called iCORPP, to simultaneously estimate the current world state, reason about world dynamics, and construct task-oriented controllers. In this process, robot decision-making problems are decomposed into two interdependent (smaller) subproblems that focus on reasoning to "understand the world" and planning to "achieve the goal" respectively. Contextual knowledge is represented in the reasoning component, which makes the planning component epistemic and enables active information gathering. The developed algorithm has been implemented and evaluated both in simulation and on real robots using everyday service tasks, such as indoor navigation, dialog management, and object delivery. Results show significant improvements in scalability, efficiency, and adaptiveness, compared to competitive baselines including handcrafted action policies.

Task-Motion Planning for Safe and Efficient Urban Driving

Autonomous vehicles need to plan at the task level to compute a sequence of symbolic actions, such as merging left and turning right, to fulfill people's service requests, where efficiency is the main concern. At the same time, the vehicles must compute continuous trajectories to perform actions at the motion level, where safety is the most important. Task-motion planning in autonomous driving faces the problem of maximizing task-level efficiency while ensuring motion-level safety. To this end, we develop algorithm Task-Motion Planning for Urban Driving (TMPUD) that, for the first time, enables the task and motion planners to communicate about the safety level of driving behaviors. TMPUD has been evaluated using a realistic urban driving simulation platform. Results suggest that TMPUD performs significantly better than competitive baselines from the literature in efficiency, while ensuring the safety of driving behaviors.