Background

Indian Railways is one of the largest rail networks in the world, serving millions of passengers daily across thousands of stations, platforms, and train coaches. Ensuring the safety and security of passengers and railway assets is a critical responsibility of the Railway Protection Force (RPF).Drug trafficking through railway networks and threats arising from explosives and Improvised Explosive Devices (IEDs) have emerged as major security concerns. During the year 2025, RPF recovered narcotic substances worth approximately Rs. 300 Crores in more than 2100 instances.However, as per data of Narcotic Control Bureau (NCB), nearly 15-20% of drug trafficking is routed through the railway network. Similarly, recent incidents involving use of high explosives such as RDX on railway tracks highlight the vulnerability of railway infrastructure to hostile activities.At present, Indian Railways does not possess any dedicated mobile quadruped or handheld system for real-time field detection of narcotics and explosives. This severely limits the capability of RPF personnel to conduct rapid, non-intrusive screening at station entry points, platforms, inside train coaches, and during luggage or parcel screening operations. Therefore, there is an urgent requirement for a modern, technology-driven, ruggedised, and easy-to-operate detection system suitable for Indian Railways operational conditions.

Description

The proposed problem statement envisages development of an AI-enabled Mobile (Quadruped) Device/System and Handheld Device/System for real-time detection of narcotics and explosives across Indian Railways.The Mobile (Quadruped) Device/System should function as an intelligent robotic surveillance platform capable of operating in hazardous, complex, and GPS-denied environments. The system should support autonomous or semi-autonomous navigation using LiDAR-based mapping, sensor fusion, thermal and optical imaging systems, and real-time video surveillance. It should be capable of operating in dusty, humid, high-temperature, low-light, and uneven railway environments including ballast areas, yards, tunnels, platforms, and coaches.The quadruped system should support underframe inspection of coaches/wagons, yard surveillance, night patrolling, bomb detection assistance, narcotics detection, facial recognition and matching, and inspection of luggage and concealed areas inside train coaches. The system should also support secure wireless communication, onboard data logging, real-time transmission to control centres, obstacle detection and avoidance, fail-safe mechanisms, and long-duration deployment capability.The Handheld Device/System should be lightweight, ruggedised, easy to operate, and deployable by RPF personnel with minimal training. It should support offline and online operation, encrypted data storage, real-time alerts, GPS tagging, automatic event logging, multilingual interface, and integration with centralized monitoring systems. The device should enable non-intrusive screening crowded railway environments and support wireless transmission of alerts and threat information to control rooms or designated supervisors. Both systems should be capable of detecting a broad spectrum of narcotics including heroin, cocaine, methamphetamine, cannabis derivatives, opium derivatives, semi-synthetic and synthetic narcotics, as well as explosives including RDX, TNT, PETN, TATP, C4, dynamite, ammonium nitrate compounds, gunpowder, and pyrotechnics.

Expected Solution

A cost-effective, ruggedised, Al-enabled Mobile (Quadruped) Device/System and Handheld Device/System should be developed for real-time detection of narcotics and explosives across Indian Railways.The proposed solution should support rapid, non-intrusive, and real-time detection capability at railway stations, platforms, train coaches, luggage screening points, yards, and other vulnerable railway locations. The system should provide automated alerts through sound, visual indicators, vibration, and centralized monitoring dashboards along with timestamp and GPS-based event logging.The quadruped system should support autonomous patrolling, under-carriage inspection, thermal imaging, facial recognition, bomb detection support, and surveillance operations in hazardous or inaccessible areas. The handheld system should support quick deployment, easy usability, offline data storage, synchronization after network restoration, multilingual operation, and integration with Railway security infrastructure. The overall solution should be operationally sustainable, low-maintenance, scalable for largescale deployment, and suitable for continuous deployment under diverse Indian Railways operational and climatic conditions.

Description

Research and develop a concept design of a warehouse automation robot platform and a modular attachment for it, using Autodesk Fusion.

Re-imagine their design and optimize for additive manufacturing.

The idea submission consists of two mandatory concept development challenges Part A – Universal Mobile Robot Platform (AGV/AMR Base) Develop a concept design of a universal Autonomous Mobile Robot (AMR) / Automated Guided Vehicle (AGV) chassis that serves as a common mobile platform for warehouse automation.

The platform should support multiple interchangeable attachments while considering structural integrity, payload capacity, weight reduction, modularity, manufacturability, and ease of maintenance.

Part B – Modular Functional Attachments Develop a concept design for any one modular attachment that integrates with the universal platform to perform specific warehouse automation tasks.

Example attachments include bin handling, pallet handling, conveyor transfer, robotic picking, inventory scanning, inspection, or any other innovative warehouse automation module.

Students should use Fusion features such as Generative Design, Topology Optimization, Additive Build, and Simulation.

The redesigned components should demonstrate innovation, enhanced functionality, improved efficiency, and optimized material usage while being suitable for additive manufacturing.

Participation Guidelines For Idea Submission Each student team should submit Fusion public link of the Conceptual Design as described in Part-A and Part-B of the above problem statement and a PowerPoint presentation (5-7 Slides).

Designs should be created using ONLY Autodesk Fusion and not copied or taken from any other source.

AI Generated content is NOT ALLOWED.

For Grand Finale*: Students must use Autodesk Fusion to design, and 3D print final design of specific components (scaled down to machine size) within the given time period and present the following to the jury members: PPT explaining the final project Final 3D prints Public link of the design Rendered images NOTE *Grand Finale details to be revealed on competition day.

Attach Marking Criteria Table here* Faculty (SIH SPOC) Form Teams choosing to submit idea for Autodesk’s problem statement are required to request their faculty (SIH SPOC) to fill this 'Mandatory Form'.

Autodesk Fusion Autodesk Fusion combines Additive Manufacturing (3D printing) capabilities with Generative Design features.

It allows users to optimize designs for 3D printing, generate support structures, and explore numerous design options using algorithms.

This integration enables the creation of complex and optimized parts using 3D printing technologies.

Students and educators can click Here to get FREE access to Fusion.

Background

India is highly vulnerable to natural disasters including floods, cyclones,earthquakes, landslides, and flash floods, which often result in damaged infrastructure, inaccessible terrain, and delayed rescue operations. During the first few critical hours after a disaster, responders need rapid situational awareness to locate survivors, assess hazards, and prioritize rescue efforts.Traditional ground-based assessments can be slow, dangerous, and resource-intensive, particularly in remote or heavily damaged areas. Autonomous drones equipped with on-device AI can provide real-time aerial intelligence while operating in environments with limited connectivity.

Description

Develop an autonomous drone system capable of navigating disaster-affected areas and performing real-time detection of survivors and hazards using on-device AI. The drone should use RGB and thermal cameras to identify stranded individuals, detect signs of human presence, and recognize environmental hazards such as fire, floodwaters, damaged structures, exposed electrical lines,debris, landslides, or chemical leaks. The solution must process data locally on the drone to ensure low latency and continued operation even when network connectivity is unavailable. The drone should autonomously map affected regions,generate situational reports, and transmit actionable insights to emergency response teams. This concept aligns with existing edge-AI drone approaches for incident response and disaster assessment.

Expected Solution

The proposed solution should include some or all of the following: Autonomous Navigation GPS-enabled and GPS-denied navigation capabilities using AI, SLAM, and obstacle avoidance for operation in damaged environments. On-Device AI Inference Real-time detection of people, survivors, and disaster-related hazards without dependence on cloud connectivity. Multi-Sensor Fusion Integration of RGB cameras, thermal cameras, IMU,and GPS sensors for accurate identification and localization of victims. Hazard Classification Detection and classification of floods, fires, smoke,debris, unstable structures, landslide zones, and other safety threats. Geo-Tagged Mapping Creation of live disaster maps highlighting survivor locations, hazard zones, and safe access routes for rescue teams. Emergency Alerting Automatic generation of alerts and prioritized rescue recommendations based on detected risks. Offline Resilience Ability to function in communication-constrained environments with optional 5G/Wi-Fi connectivity when available. Command Center Dashboard Visualization of drone feeds, detected survivors, hazard markers, and mission status to support disaster management agencies.