arXiv subjects

Mark Roberts

Publications and source records attributed to Mark Roberts.

At least 19 recordsLinked to original sources

arXiv2025

POrTAL: Plan-Orchestrated Tree Assembly for Lookahead

When tasking robots in partially observable environments, these robots must efficiently and robustly plan to achieve task goals under uncertainty. Although many probabilistic planning algorithms exist for this purpose, these algorithms can be inefficient if executed with the robot's limited computational resources, or may produce policies that take more steps than expected to achieve the goal. We therefore created a new, lightweight, probabilistic planning algorithm, Plan-Orchestrated Tree Assembly for Lookahead (POrTAL), that combines the strengths of two baseline planning algorithms, FF-Replan and POMCP. We demonstrate that POrTAL is an anytime algorithm that generally outperforms these baselines in terms of the final executed plan length given bounded computation time, especially for problems with only moderate levels of uncertainty.

cs.RO↗

arXiv2025

Procedural Knowledge Improves Agentic LLM Workflows

Large language models (LLMs) often struggle when performing agentic tasks without substantial tool support, prom-pt engineering, or fine tuning. Despite research showing that domain-dependent, procedural knowledge can dramatically increase planning efficiency, little work evaluates its potential for improving LLM performance on agentic tasks that may require implicit planning. We formalize, implement, and evaluate an agentic LLM workflow that leverages procedural knowledge in the form of a hierarchical task network (HTN). Empirical results of our implementation show that hand-coded HTNs can dramatically improve LLM performance on agentic tasks, and using HTNs can boost a 20b or 70b parameter LLM to outperform a much larger 120b parameter LLM baseline. Furthermore, LLM-created HTNs improve overall performance, though less so. The results suggest that leveraging expertise--from humans, documents, or LLMs--to curate procedural knowledge will become another important tool for improving LLM workflows.

cs.AI↗

arXiv2025

Landmark-Assisted Monte Carlo Planning

Landmarks$\unicode{x2013}$conditions that must be satisfied at some point in every solution plan$\unicode{x2013}$have contributed to major advancements in classical planning, but they have seldom been used in stochastic domains. We formalize probabilistic landmarks and adapt the UCT algorithm to leverage them as subgoals to decompose MDPs; core to the adaptation is balancing between greedy landmark achievement and final goal achievement. Our results in benchmark domains show that well-chosen landmarks can significantly improve the performance of UCT in online probabilistic planning, while the best balance of greedy versus long-term goal achievement is problem-dependent. The results suggest that landmarks can provide helpful guidance for anytime algorithms solving MDPs.

cs.AI↗

arXiv2025

HTN Plan Repair Algorithms Compared: Strengths and Weaknesses of Different Methods

This paper provides theoretical and empirical comparisons of three recent hierarchical plan repair algorithms: SHOPFixer, IPyHOPPER, and Rewrite. Our theoretical results show that the three algorithms correspond to three different definitions of the plan repair problem, leading to differences in the algorithms' search spaces, the repair problems they can solve, and the kinds of repairs they can make. Understanding these distinctions is important when choosing a repair method for any given application. Building on the theoretical results, we evaluate the algorithms empirically in a series of benchmark planning problems. Our empirical results provide more detailed insight into the runtime repair performance of these systems and the coverage of the repair problems solved, based on algorithmic properties such as replanning, chronological backtracking, and backjumping over plan trees.

cs.AI↗

arXiv2025

Uncertainty Expression for Human-Robot Task Communication

An underlying assumption of many existing approaches to human-robot task communication is that the robot possesses a sufficient amount of environmental domain knowledge, including the locations of task-critical objects. This assumption is unrealistic if the locations of known objects change or have not yet been discovered by the robot. In this work, our key insight is that in many scenarios, robot end users possess more scene insight than the robot and need ways to express it. Presently, there is a lack of research on how solutions for collecting end-user scene insight should be designed. We thereby created an Uncertainty Expression System (UES) to investigate how best to elicit end-user scene insight. The UES allows end users to convey their knowledge of object uncertainty using either: (1) a precision interface that allows meticulous expression of scene insight; (2) a painting interface by which users create a heat map of possible object locations; and (3) a ranking interface by which end users express object locations via an ordered list. We then conducted a user study to compare the effectiveness of these approaches based on the accuracy of scene insight conveyed to the robot, the efficiency at which end users are able to express this scene insight, and both usability and task load. Results indicate that the rank interface is more user friendly and efficient than the precision interface, and that the paint interface is the least accurate.

cs.HC↗

arXiv2025

Automating Curriculum Learning for Reinforcement Learning using a Skill-Based Bayesian Network

A major challenge for reinforcement learning is automatically generating curricula to reduce training time or improve performance in some target task. We introduce SEBNs (Skill-Environment Bayesian Networks) which model a probabilistic relationship between a set of skills, a set of goals that relate to the reward structure, and a set of environment features to predict policy performance on (possibly unseen) tasks. We develop an algorithm that uses the inferred estimates of agent success from SEBN to weigh the possible next tasks by expected improvement. We evaluate the benefit of the resulting curriculum on three environments: a discrete gridworld, continuous control, and simulated robotics. The results show that curricula constructed using SEBN frequently outperform other baselines.

cs.AI↗

arXiv2024

Composing Option Sequences by Adaptation: Initial Results

Robot manipulation in real-world settings often requires adapting the robot's behavior to the current situation, such as by changing the sequences in which policies execute to achieve the desired task. Problematically, however, we show that composing a novel sequence of five deep RL options to perform a pick-and-place task is unlikely to successfully complete, even if their initiation and termination conditions align. We propose a framework to determine whether sequences will succeed a priori, and examine three approaches that adapt options to sequence successfully if they will not. Crucially, our adaptation methods consider the actual subset of points that the option is trained from or where it ends: (1) trains the second option to start where the first ends; (2) trains the first option to reach the centroid of where the second starts; and (3) trains the first option to reach the median of where the second starts. Our results show that our framework and adaptation methods have promise in adapting options to work in novel sequences.

cs.RO↗

arXiv2024

Towards Online Safety Corrections for Robotic Manipulation Policies

Recent successes in applying reinforcement learning (RL) for robotics has shown it is a viable approach for constructing robotic controllers. However, RL controllers can produce many collisions in environments where new obstacles appear during execution. This poses a problem in safety-critical settings. We present a hybrid approach, called iKinQP-RL, that uses an Inverse Kinematics Quadratic Programming (iKinQP) controller to correct actions proposed by an RL policy at runtime. This ensures safe execution in the presence of new obstacles not present during training. Preliminary experiments illustrate our iKinQP-RL framework completely eliminates collisions with new obstacles while maintaining a high task success rate.

cs.RO↗

arXiv2024

Automatically Learning HTN Methods from Landmarks

Hierarchical Task Network (HTN) planning usually requires a domain engineer to provide manual input about how to decompose a planning problem. Even HTN-MAKER, a well-known method-learning algorithm, requires a domain engineer to annotate the tasks with information about what to learn. We introduce CURRICULAMA, an HTN method learning algorithm that completely automates the learning process. It uses landmark analysis to compose annotated tasks and leverages curriculum learning to order the learning of methods from simpler to more complex. This eliminates the need for manual input, resolving a core issue with HTN-MAKER. We prove CURRICULAMA's soundness, and show experimentally that it has a substantially similar convergence rate in learning a complete set of methods to HTN-MAKER.

cs.AI↗

arXiv2024

Goal-Oriented End-User Programming of Robots

End-user programming (EUP) tools must balance user control with the robot's ability to plan and act autonomously. Many existing task-oriented EUP tools enforce a specific level of control, e.g., by requiring that users hand-craft detailed sequences of actions, rather than offering users the flexibility to choose the level of task detail they wish to express. We thereby created a novel EUP system, Polaris, that in contrast to most existing EUP tools, uses goal predicates as the fundamental building block of programs. Users can thereby express high-level robot objectives or lower-level checkpoints at their choosing, while an off-the-shelf task planner fills in any remaining program detail. To ensure that goal-specified programs adhere to user expectations of robot behavior, Polaris is equipped with a Plan Visualizer that exposes the planner's output to the user before runtime. In what follows, we describe our design of Polaris and its evaluation with 32 human participants. Our results support the Plan Visualizer's ability to help users craft higher-quality programs. Furthermore, there are strong associations between user perception of the robot and Plan Visualizer usage, and evidence that robot familiarity has a key role in shaping user experience.

cs.RO↗

arXiv2024

Considerations for End-User Development in the Caregiving Domain

As service robots become more capable of autonomous behaviors, it becomes increasingly important to consider how people communicate with a robot what task it should perform and how to do the task. Accordingly, there has been a rise in attention to end-user development (EUD) interfaces, which enable non-roboticist end users to specify tasks for autonomous robots to perform. However, state-of-the-art EUD interfaces are often constrained through simplified domains or restrictive end-user interaction. Motivated by prior qualitative design work that explores how to integrate a care robot in an assisted living community, we discuss the challenges of EUD in this complex domain. One set of challenges stems from different user-facing representations, e.g., certain tasks may lend themselves better to rule-based trigger-action representations, whereas other tasks may be easier to specify via sequences of actions. The other stems from considering the needs of multiple stakeholders, e.g., caregivers and residents of the facility may all create tasks for the robot, but the robot may not be able to share information about all tasks with all residents due to privacy concerns. We present scenarios that illustrate these challenges and also discuss possible solutions.

cs.RO↗

arXiv2024

Human-Centric Goal Reasoning with Ripple-Down Rules

ActorSim is a goal reasoning framework developed at the Naval Research Laboratory. Originally, all goal reasoning rules were hand-crafted. This work extends ActorSim with the capability of learning by demonstration, that is, when a human trainer disagrees with a decision made by the system, the trainer can take over and show the system the correct decision. The learning component uses Ripple-Down Rules (RDR) to build new decision rules to correctly handle similar cases in the future. The system is demonstrated using the RoboCup Rescue Agent Simulation, which simulates a city-wide disaster, requiring emergency services, including fire, ambulance and police, to be dispatched to different sites to evacuate civilians from dangerous situations. The RDRs are implemented in a scripting language, FrameScript, which is used to mediate between ActorSim and the agent simulator. Using Ripple-Down Rules, ActorSim can scale to an order of magnitude more goals than the previous version.

cs.RO↗

arXiv2023

New Horizons: Pioneering Pharmaceutical R&D with Generative AI from lab to the clinic -- an industry perspective

The rapid advance of generative AI is reshaping the strategic vision for R&D across industries. The unique challenges of pharmaceutical R&D will see applications of generative AI deliver value along the entire value chain from early discovery to regulatory approval. This perspective reviews these challenges and takes a three-horizon approach to explore the generative AI applications already delivering impact, the disruptive opportunities which are just around the corner, and the longer-term transformation which will shape the future of the industry. Selected applications are reviewed for their potential to drive increase productivity, accelerate timelines, improve the quality of research, data and decision making, and support a sustainable future for the industry. Recommendations are given for Pharma R&D leaders developing a generative AI strategy today which will lay the groundwork for getting real value from the technology and safeguarding future growth. Generative AI is today providing new, efficient routes to accessing and combining organisational data to drive productivity. Next, this impact will reach clinical development, enhancing the patient experience, driving operational efficiency, and unlocking digital innovation to better tackle the future burden of disease. Looking to the furthest horizon, rapid acquisition of rich multi-omics data, which capture the 'language of life', in combination with next generation AI technologies will allow organisations to close the loop around phases of the pipeline through rapid, automated generation and testing of hypotheses from bench to bedside. This provides a vision for the future of R&D with sustainability at the core, with reduced timescales and reduced dependency on resources, while offering new hope to patients to treat the untreatable and ultimately cure diseases.

q-bio.QM↗

arXiv2022

Understanding CNN Fragility When Learning With Imbalanced Data

Convolutional neural networks (CNNs) have achieved impressive results on imbalanced image data, but they still have difficulty generalizing to minority classes and their decisions are difficult to interpret. These problems are related because the method by which CNNs generalize to minority classes, which requires improvement, is wrapped in a blackbox. To demystify CNN decisions on imbalanced data, we focus on their latent features. Although CNNs embed the pattern knowledge learned from a training set in model parameters, the effect of this knowledge is contained in feature and classification embeddings (FE and CE). These embeddings can be extracted from a trained model and their global, class properties (e.g., frequency, magnitude and identity) can be analyzed. We find that important information regarding the ability of a neural network to generalize to minority classes resides in the class top-K CE and FE. We show that a CNN learns a limited number of class top-K CE per category, and that their number and magnitudes vary based on whether the same class is balanced or imbalanced. This calls into question whether a CNN has learned intrinsic class features, or merely frequently occurring ones that happen to exist in the sampled class distribution. We also hypothesize that latent class diversity is as important as the number of class examples, which has important implications for re-sampling and cost-sensitive methods. These methods generally focus on rebalancing model weights, class numbers and margins; instead of diversifying class latent features through augmentation. We also demonstrate that a CNN has difficulty generalizing to test data if the magnitude of its top-K latent features do not match the training set. We use three popular image datasets and two cost-sensitive algorithms commonly employed in imbalanced learning for our experiments.

cs.CV↗

arXiv2016

Cost-Optimal Algorithms for Planning with Procedural Control Knowledge

There is an impressive body of work on developing heuristics and other reasoning algorithms to guide search in optimal and anytime planning algorithms for classical planning. However, very little effort has been directed towards developing analogous techniques to guide search towards high-quality solutions in hierarchical planning formalisms like HTN planning, which allows using additional domain-specific procedural control knowledge. In lieu of such techniques, this control knowledge often needs to provide the necessary search guidance to the planning algorithm, which imposes a substantial burden on the domain author and can yield brittle or error-prone domain models. We address this gap by extending recent work on a new hierarchical goal-based planning formalism called Hierarchical Goal Network (HGN) Planning to develop the Hierarchically-Optimal Goal Decomposition Planner (HOpGDP), an HGN planning algorithm that computes hierarchically-optimal plans. HOpGDP is guided by $h_{HL}$, a new HGN planning heuristic that extends existing admissible landmark-based heuristics from classical planning to compute admissible cost estimates for HGN planning problems. Our experimental evaluation across three benchmark planning domains shows that HOpGDP compares favorably to both optimal classical planners due to its ability to use domain-specific procedural knowledge, and a blind-search version of HOpGDP due to the search guidance provided by $h_{HL}$.

cs.AI↗

arXiv2015

Gradient systems on coupled cell networks

For networks of coupled dynamical systems we characterize admissible functions, that is, functions whose gradient is an admissible vector field. The schematic representation of a gradient network dynamical system is of an undirected cell graph, and we use tools from graph theory to deduce the general form of such functions, relating it to the topological structure of the graph defining the network. The coupling of pairs of dynamical systems cells is represented by edges of the graph, and from spectral graph theory we detect the existence and nature of equilibria of the gradient system from the critical points of the coupling function. In particular, we study fully synchronous and 2-state patterns of equilibria on regular graphs.These are two special types of equilibrium configurations for gradient networks. We also investigate equilibrium configurations of S1-invariant admissible functions on a ring of cells.

math.DS↗

arXiv2009

Recent Developments in the Skyrme Model

In this talk, we describe recent developments in the Skyrme model. Our main focus is on discussing various effects which need to be taken into account, when calculating the properties of light atomic nuclei in the Skyrme model. We argue that an important step is to understand "spinning Skyrmions" and discuss the theory of relative equilibria in this context.

hep-th↗

arXiv2004

Point vortices on the sphere: stability of relative equilibria

We describe the linear and nonlinear stability and instability of certain symmetric configurations of point vortices on the sphere forming relative equilibria. These configurations consist of one or two rings, and a ring with one or two polar vortices. Such configurations have dihedral symmetry, and the symmetry is used to block diagonalize the relevant matrices, to distinguish the subspaces on which their eigenvalues need to be calculated, and also to describe the bifurcations that occur as eigenvalues pass through zero.

math.DS↗