Gautham Das

Dr. Gautham Das

Lincoln Institute for Agri-food Technology, University of Lincoln, Lincoln, Lincolnshire, UK
orcid

Research Focus & Metrics

Academic Career Length

16Years (2011-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
20 November 2023 in Machines
Verified
Journal Article
Open access
PDF file
JHJames Richard Heselden
James Richard Heselden
GDGautham Das
Gautham Das
The benefits of multi-robot systems are substantial, bringing gains in efficiency, quality, and cost, and they are useful in a wide range of environments from warehouse automation, to agriculture and even extend in part to entertainment. In multi-robot system research, the main focus is on ensuring efficient coordination in the operation of the robots, both in task allocation and navigation. However, much of this research seldom strays from the theoretical bounds; there are many reasons for this, with the most-prominent and -impactful being resource limitations. This is especially true for research in areas such as multi-robot path planning (MRPP) and navigation coordination. This is a large issue in practice as many approaches are not designed with meaningful real-world implications in mind and are not scalable to large multi-robot systems. This survey aimed to look into the coordination and path-planning issues and challenges faced when working with multi-robot systems, especially those using a prioritised planning approach, and identify key areas that are not well-explored and the scope of applying existing MRPP approaches to real-world settings.

26 December 2024 in Journal of Field Robotics
Verified
Journal Article
Open access
GDGautham Das
Gautham Das
GCGrzegorz Cielniak
Grzegorz Cielniak
JHJames Heselden
James Heselden
SPSimon Pearson
Simon Pearson
FDFrancesco Del Duchetto
Francesco Del Duchetto
PFPal From
Pal From
Agricultural robots offer a viable solution to the critical challenges of productivity and sustainability of modern agriculture. The widespread deployment of agricultural robotic fleets, however, is still hindered by the overall system's complexity, requiring the integration of several nontrivial components for the operation of each robot but also the orchestration of robots working with each other and human workers. This paper proposes a topological map as the unifying representation and computational model to facilitate the smooth deployment of robotic fleets in agriculture. This topological abstraction of the system state (probabilistic estimates of the functional states and locations of the agents in the environment abstracted to the topological map representations—e.g., human picker at a node and robot traversing on edge ) results in an efficient representation of large‐scale environments (in many hectares), but also offers the scalable and efficient operation of the entire fleet and allows for ex situ modeling and analysis of operations. The practical use of the proposed framework is demonstrated in a horticultural use case with a fleet of robots supporting the work of human fruit pickers. The critical components of the system are analyzed and evaluated in deployment in both realistic digital twin and real‐life soft fruit farms of different scales, demonstrating the scalability and effectiveness of the proposed framework. The presented framework is general and should be easy to adopt in other multirobot/multihuman scenarios, such as warehouse logistics, cleaning, and maintenance of public spaces.

27 March 2023
Verified
Conference Paper
Open access
ZZZuyuan Zhu
Zuyuan Zhu
GDGautham Das
Gautham Das
MHMarc Hanheide
Marc Hanheide
Multi-robot systems (MRS) are currently being introduced in many in-field logistics operations in large environments such as warehouses and commercial soft-fruit production. Collision avoidance is a critical problem in MRS as it may introduce deadlocks during the motion planning. In this work, a discretised topological map representation is used for low-cost route planning of individual robots as well as to easily switch the navigation actions depending on the constraints in the environment. However, this topological map could also have bottlenecks which leads to deadlocks and low transportation efficiency when used for an MRS. In this paper, we propose a resource container based Request-Release-Interrupt (RRI) algorithm that constrains each topological node with a capacity of one entity and therefore helps to avoid collisions and detect deadlocks. Furthermore, we integrate a Genetic Algorithm (GA) with Discrete Event Simulation (DES) for optimising the topological map to reduce deadlocks and improve transportation efficiency in logistics tasks. Performance analysis of the proposed algorithms are conducted after running a set of simulations with multiple robots and different maps. The results validate the effectiveness of our algorithms.

27 September 2023 in Preprints.org
Verified
Preprint
Open access
PDF file
JHJames Richard Heselden
James Richard Heselden
GDGautham Das
Gautham Das
The benefits of multi-robot systems are substantial, bringing gains in efficiency, quality, and cost, and are useful in a wide range of environments from warehouse automation, to agriculture, and even extend in part to entertainment. In multi-robot system research, the main focus is on ensuring efficient coordination in the operation of the robots, both in task allocation and navigation. However, much of this research seldom strays from theoretical bounds; there are many reasons for this, with the most prominent and impactful being resource limitations. This is especially true for research in areas such as multi-robot path planning (MRPP) and navigation coordination. This is a large issue in practice as many approaches are not designed with meaningful real-world implications in mind and are not scalable to large multi-robot systems. This survey aims to look into the coordination and path-planning issues and challenges faced when working with multi-robot systems, especially those using a prioritised planning approach and identify key areas which are not well-explored and the scope of applying existing MRPP approaches to real-world settings.

24 December 2024 in Machines
Verified
Journal Article
Open access
PDF file
JHJames Richard Heselden
James Richard Heselden
DPDimitris Paparas
Dimitris Paparas
RSRobert Liam Stevenson
Robert Liam Stevenson
GDGautham Das
Gautham Das
Accurate localisation is key for the autonomy of mobile robots. Fiducial localisation utilises relative positions of markers physically deployed across an environment to determine a localisation estimate for a robot. Fiducial markers are strictly designed, with very limited flexibility in appearance. This often results in a “trade-off” between visual customisation, library size, and occlusion resilience. Many fiducial localisation approaches vary in their position estimation over time, leading to instability. The Stable Fiducial Marker System (STag) was designed to address this limitation with the use of a two-stage homography detection. Through its combined square and circle detection phases, it can refine detection stability. In this work, we explore the utility of STag as a basis for a stable mobile robot localisation system. Key marker restrictions are addressed in this work through contributions of three new chromatic STag marker types. The hue/greyscale STag marker set addresses constraints in customisability, the high-capacity STag marker set addresses limitations in library size, and the high-occlusion STag marker set improves resilience to occlusions. These are designed with compatibility with the STag detection system, requiring only preprocessing steps for enhanced detection. They are assessed against the existing STag markers and each shows clear improvements. Further, we explore the viability of various materials for marker fabrication, for use in outdoor and low-light conditions. This includes the exploration of “active” materials which induce effects such as retro-reflectance and photo-luminescence. Detection rates are experimentally assessed across lighting conditions, with “active” markers assessed on the practicality of their effects. To encapsulate this work, we have developed a full end-to-end deployment for fiducial localisation under the STag system. It is shown to function for both on-board and off-board localisation, with deployment in practical robot trials. As a part of this contribution, the associated software for marker set generation/detection, physical marker fabrication, and end-to-end localisation has been released as an open source distribution.

31 May 2025 in Robotics
Verified
Journal Article
Open access
PDF file
LRLaurence Roberts-Elliott
Laurence Roberts-Elliott
GDGautham Das
Gautham Das
GCGrzegorz Cielniak
Grzegorz Cielniak
One of the most commonly performed environmental explorations is soil sampling to identify soil properties of agricultural fields, which can inform the farmer about the variable rate treatment of fertilisers in precision agriculture. However, traditional manual methods are slow, costly, and yield low spatial resolution. Deploying multiple robots with proximal sensors can address this challenge by parallelising the sampling process. Yet, multi-robot soil sampling is under-explored in the literature. This paper proposes an auction-based multi-robot task allocation that efficiently coordinates the sampling, coupled with a dynamic sampling strategy informed by Kriging variance from interpolation. This strategy aims to reduce the number of samples needed for accurate mapping by exploring and sampling areas that maximise information gained per sample. The key innovative contributions include (1) a novel Distance Over Variance (DOV) bid calculation for auction-based multi-robot task allocation, which incentivises sampling in high-uncertainty, nearby areas; (2) integration of the DOV bid calculation into the cheapest insertion heuristic for task queuing; and (3) thresholding of newly created tasks at locations with low Kriging variance to drop those unlikely to offer significant information gain. The proposed methods were evaluated through comparative simulated experiments using historical soil compaction data. Evaluation trials demonstrate the suitability of the DOV bid calculation combined with task dropping, resulting in substantial improvements in key performance metrics, including mapping accuracy. While the experiments were conducted in simulation, the system is compatible with ROS and the ‘move_base’ action client to allow real-world deployment. The results from these simulations indicate that the Kriging-variance-informed approach can be applied to the exploration and mapping of other soil properties (e.g., pH, soil organic carbon, etc.) and environmental data.