Arrow Research search

Author name cluster

David Smith

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

19 papers
2 author rows

Possible papers

19

AAAI Conference 2026 Conference Paper

Enhancing DPSGD via Per-Sample Momentum and Low-Pass Filtering

  • Xincheng Xu
  • Thilina Ranbaduge
  • Qing Wang
  • Thierry Rakotoarivelo
  • David Smith

Differentially Private Stochastic Gradient Descent (DPSGD) is widely used to train deep neural networks with formal privacy guarantees. However, the addition of differential privacy (DP) often degrades model accuracy by introducing both noise and bias. Existing techniques typically address only one of these issues, as reducing DP noise can exacerbate clipping bias and vice-versa. In this paper, we propose a novel method, DP-PMLF, which integrates per-sample momentum with a low-pass filtering strategy to simultaneously mitigate DP noise and clipping bias. Our approach uses per-sample momentum to smooth gradient estimates prior to clipping, thereby reducing sampling variance. It further employs a post-processing low-pass filter to attenuate high-frequency DP noise without consuming additional privacy budget. We provide a theoretical analysis demonstrating an improved convergence rate under rigorous DP guarantees, and our empirical evaluations reveal that DP-PMLF significantly enhances the privacy-utility trade-off compared to several state-of-the-art DPSGD variants.

PDF Details DOI

ICRA Conference 2025 Conference Paper

How About Them Apples: 3D Pose and Cluster Estimation of Apple Fruitlets in a Commercial Orchard

  • Ans Qureshi
  • David Smith
  • Trevor Gee
  • Ho Seok Ahn
  • Benjamin McGuinness
  • Catherine Downes
  • Rahul Jangali
  • Kale Black

Aotearoa's apple industry struggles to maintain the skilled workforce required for fruitlet thinning each year. Skilled labourers play a pivotal role in managing crop loads by precisely thinning fruitlets to a desired number to achieve the desired spacing for high-quality apple growth. This complex task requires accurate mapping of the fruitlets along each branch. This paper presents a novel vision system capable of mapping the orientation and clustering information of apple fruitlets. Fruitlet pose estimation has been validated against data collected from a real-world commercial apple orchard. The results show an improved counting accuracy of 83. 97% on prior implementations, an orientation estimate accuracy of 88. 1%, and a clustering accuracy of 94. 3%. Future work will utilise this information to determine which fruitlets to remove and then robotically thin them from the canopy.

Details

IROS Conference 2024 Conference Paper

Archie Jnr: A Robotic Platform for Autonomous Cane Pruning of Grapevines

  • Henry Williams
  • David Smith
  • Jalil Shahabi
  • Trevor Gee
  • Ans Qureshi
  • Benjamin McGuinness
  • Scott Harvey
  • Catherine Downes

Cane pruning grapevines is a complex manual task requiring expert vine assessment to determine which canes to prune. This paper presents Archie Jnr, which was developed to autonomously assess the structure of the vine and prune the lower-quality canes as an expert pruner would. The platform has been extensively evaluated in a real-world commercial vineyard using a three-cane pruning method. The results show the effectiveness of the vision system for generating accurate assessments of a vine’s canes. The platform is also shown to be capable of successfully pruning 71. 1% of the 311 total canes that required pruning across 25 vines.

Details

IROS Conference 2024 Conference Paper

Archie Snr: A Robotic Platform for Autonomous Apple Fruitlet Thinning

  • Henry Williams
  • Ans Qureshi
  • David Smith
  • Trevor Gee
  • Benjamin McGuinness
  • Rahul Jangali
  • Kale Black
  • Scott Harvey

Apple fruitlet thinning is critical in cultivating high-quality apples, requiring an expert workforce to manage the orchard. The thinning process requires precise mapping of fruitlet clusters across the tree branches to manage the desired load for each tree. This paper presents Archie Snr, which was developed to autonomously assess the current load of the tree and thin the excess apples as an expert thinner would. The platform has been extensively evaluated in a real-world commercial orchard. The results show the platform can generate an average load count accuracy of 82. 1% with a recall of 93. 3%. The system was then able to successfully thin 66. 14% of the fruitlets from the canopy.

Details

IROS Conference 2023 Conference Paper

Seeing the Fruit for the Leaves: Robotically Mapping Apple Fruitlets in a Commercial Orchard

  • Ans Qureshi
  • David Smith
  • Trevor Gee
  • Mahla Nejati
  • Jalil Shahabi
  • JongYoon Lim
  • Ho Seok Ahn
  • Benjamin McGuinness

Aotearoa New Zealand has a strong and growing apple industry but struggles to access workers to complete skilled, seasonal tasks such as thinning. To ensure effective thinning and make informed decisions on a per-tree basis, it is crucial to accurately measure the crop load of individual apple trees. However, this task poses challenges due to the dense foliage that hides the fruitlets within the tree structure. In this paper, we introduce the vision system of an automated apple fruitlet thinning robot, developed to tackle the labor shortage issue. This paper presents the initial design, implementation, and evaluation specifics of the system. The platform straddles the 3. 4 m tall 2D apple canopy structures to create an accurate map of the fruitlets on each tree. We show that this platform can measure the fruitlet load on an apple tree by scanning through both sides of the branch. The requirement of an overarching platform was justified since two-sided scans had a higher counting accuracy of 81. 17% than one-sided scans at 73. 7%. The system was also demonstrated to produce size estimates within 5. 9% RMSE of their true size.

Details

IJCAI Conference 2021 Conference Paper

A Unifying Bayesian Formulation of Measures of Interpretability in Human-AI Interaction

  • Sarath Sreedharan
  • Anagha Kulkarni
  • David Smith
  • Subbarao Kambhampati

Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under differing assumptions, thus precluding the possibility of designing a single framework that captures these measures under the same assumptions. In this paper, we present a unifying Bayesian framework that models a human observer's evolving beliefs about an agent and thereby define the problem of Generalized Human-Aware Planning. We will show that the definitions of interpretability measures like explicability, legibility and predictability from the prior literature fall out as special cases of our general framework. Through this framework, we also bring a previously ignored fact to light that the human-robot interactions are in effect open-world problems, particularly as a result of modeling the human's beliefs over the agent. Since the human may not only hold beliefs unknown to the agent but may also form new hypotheses about the agent when presented with novel or unexpected behaviors.

PDF Details DOI

IJCAI Conference 2019 Conference Paper

Why Can’t You Do That HAL? Explaining Unsolvability of Planning Tasks

  • Sarath Sreedharan
  • Siddharth Srivastava
  • David Smith
  • Subbarao Kambhampati

Explainable planning is widely accepted as a prerequisite for autonomous agents to successfully work with humans. While there has been a lot of research on generating explanations of solutions to planning problems, explaining the absence of solutions remains an open and under-studied problem, even though such situations can be the hardest to understand or debug. In this paper, we show that hierarchical abstractions can be used to efficiently generate reasons for unsolvability of planning problems. In contrast to related work on computing certificates of unsolvability, we show that these methods can generate compact, human-understandable reasons for unsolvability. Empirical analysis and user studies show the validity of our methods as well as their computational efficacy on a number of benchmark planning domains.

PDF Details

AAAI Conference 2018 Conference Paper

Contrastive Training for Models of Information Cascades

  • Shaobin Xu
  • David Smith

This paper proposes a model of information cascades as directed spanning trees (DSTs) over observed documents. In addition, we propose a contrastive training procedure that exploits partial temporal ordering of node infections in lieu of labeled training links. This combination of model and unsupervised training makes it possible to improve on models that use infection times alone and to exploit arbitrary features of the nodes and of the text content of messages in information cascades. With only basic node and time lag features similar to previous models, the DST model achieves performance with unsupervised training comparable to strong baselines on a blog network inference task. Unsupervised training with additional content features achieves significantly better results, reaching half the accuracy of a fully supervised model.

PDF Details

IJCAI Conference 2017 Conference Paper

Order Statistics for Probabilistic Graphical Models

  • David Smith
  • Sara Rouhani
  • Vibhav Gogate

We consider the problem of computing r-th order statistics, namely finding an assignment having rank r in a probabilistic graphical model. We show that the problem is NP-hard even when the graphical model has no edges (zero-treewidth models) via a reduction from the partition problem. We use this reduction, specifically a pseudo-polynomial time algorithm for number partitioning to yield a pseudo-polynomial time approximation algorithm for solving the r-th order statistics problem in zero- treewidth models. We then extend this algorithm to arbitrary graphical models by generalizing it to tree decompositions, and demonstrate via experimental evaluation on various datasets that our proposed algorithm is more accurate than sampling algorithms.

PDF Details

NeurIPS Conference 2015 Conference Paper

Bounding the Cost of Search-Based Lifted Inference

  • David Smith
  • Vibhav Gogate

Recently, there has been growing interest in systematic search-based and importance sampling-based lifted inference algorithms for statistical relational models (SRMs). These lifted algorithms achieve significant complexity reductions over their propositional counterparts by using lifting rules that leverage symmetries in the relational representation. One drawback of these algorithms is that they use an inference-blind representation of the search space, which makes it difficult to efficiently pre-compute tight upper bounds on the exact cost of inference without running the algorithm to completion. In this paper, we present a principled approach to address this problem. We introduce a lifted analogue of the propositional And/Or search space framework, which we call a lifted And/Or schematic. Given a schematic-based representation of an SRM, we show how to efficiently compute a tight upper bound on the time and space cost of exact inference from a current assignment and the remaining schematic. We show how our bounding method can be used within a lifted importance sampling algorithm, in order to perform effective Rao-Blackwellisation, and demonstrate experimentally that the Rao-Blackwellised version of the algorithm yields more accurate estimates on several real-world datasets.

PDF Details

RLDM Conference 2013 Conference Abstract

Parsing Multiple Feedback Signals within the Striatum

  • David Smith
  • Ana Rigney
  • Mauricio Delgado

Many brain-imaging studies have demonstrated a selective link between striatal activation and feedback. Yet, feedback is composed of multiple components with distinct properties. Notably, affective components of feedback signal whether an outcome was positive or negative while informative components of feedback signal how to adapt behavior to maximize future rewards. To dissociate affective and informative components of feedback, we utilized two card-guessing games emphasizing distinct incentive-compatible goals related to affective and informative feedback. On each trial of the Affective Card Task (ACT), sub- jects (n = 21) chose between three decks of cards that yielded variable levels of points (1, 2, and 3). The Informative Card Task (ICT) employed a similar structure except subjects received letters (D, K, and X) that appeared with different probabilities in each deck (50 %, 33 %, and 17 %). We instructed subjects that earning enough points in the ACT would allow them to play another task for monetary bonus at the conclu- sion of the experiment; however, earning this bonus money would require using information learned in the ICT. Critically, the bonus structure helps mitigate differences in the immediacy of affective and informative incentives, as both are equally delayed. Our preliminary results suggest that both types of feedback evoke activation within the striatum, with greater activation in ventral striatum for affective feedback. Collectively, our paradigm—coupled with our preliminary findings—could provide new insight into the mechanistic link between striatal dysfunction and psychopathology.

PDF Details

IJCAI Conference 2013 Conference Paper

The Inclusion-Exclusion Rule and Its Application to the Junction Tree Algorithm

  • David Smith
  • Vibhav Gogate

In this paper, we consider the inclusion-exclusion rule – a known yet seldom used rule of probabilistic inference. Unlike the widely used sum rule which requires easy access to all joint probability values, the inclusion-exclusion rule requires easy access to several marginal probability values. We therefore develop a new representation of the joint distribution that is amenable to the inclusion-exclusion rule. We compare the relative strengths and weaknesses of the inclusion-exclusion rule with the sum rule and develop a hybrid rule called the inclusionexclusion-sum (IES) rule, which combines their power. We apply the IES rule to junction trees, treating the latter as a target for knowledge compilation and show that in many cases it greatly reduces the time required to answer queries. Our experiments demonstrate the power of our approach. In particular, at query time, on several networks, our new scheme was an order of magnitude faster than the junction tree algorithm.

PDF Details DOI

AAAI Conference 2012 Conference Paper

Planning as an Iterative Process

  • David Smith

Activity planning for missions such as the Mars Exploration Rover mission presents many technical challenges, including oversubscription, consideration of time, concurrency, resources, preferences, and uncertainty. These challenges have all been addressed by the research community to varying degrees, but significant technical hurdles still remain. In addition, the integration of these capabilities into a single planning engine remains largely unaddressed. However, I argue that there is a deeper set of issues that needs to be considered – namely the integration of planning into an iterative process that begins before the goals, objectives, and preferences are fully defined. This introduces a number of technical challenges for planning, including the ability to more naturally specify and utilize constraints on the planning process, the ability to generate multiple qualitatively different plans, and the ability to provide deep explanation of plans.

PDF Details

AAAI Conference 2011 Conference Paper

Probabilistic Plan Graph Heuristic for Probabilistic Planning

  • Yolanda E-Martín
  • Maria R-Moreno
  • David Smith

This work focuses on developing domain-independent heuristics for probabilistic planning problems characterized by full observability and non-deterministic effects of actions that are expressed by probability distributions. The approach is to first search for a high probability deterministic plan using a classical planner. A novel probabilistic plan graph heuristic is used to guide the search towards high probability plans. The resulting plans can be used in a system that handles unexpected outcomes by runtime replanning. The plans can also be incrementally augmented with contingency branches for the most critical action outcomes. This abstract will describe the steps that we have taken in completing the above work and the obtained results.

PDF Details

ICRA Conference 1987 Conference Paper

Edge detection in tactile images

  • Chellappa Muthukrishnan
  • David Smith
  • Donald Myers
  • Jack Rebman
  • Antti J. Koivo

Some of the edge detection methods well known in robotic vision systems have been applied to detect edges in tactile images. Two dimensional median filtering with a 3 × 3 window size has been employed for the removal of noise present in the tactile images with excellent results. The LTS-200 tactile sensor system developed by the LORD Corporation has been used to obtain the tactile images analyzed in this research. The study has been carried out to obtain the contours of objects smaller in size than the LTS-200 sensor (with an active area of 1. 131 in. × 0. 707 in.) with a single probing operation. For larger objects, a straight line extraction method has been employed by which one can obtain the polygonal approximation of the shape of the object by sequential touching and integrating the straight lines so extracted.

Details