Bharat in Betastartup field guide
← Back to the atlas
No. 029Opportunity areaMobility and logistics

EV charging and electric mobility infrastructure

Source

The idea

Charging and mobility platforms supporting electrification.

Why this is interesting

  • Charging infrastructure succeeds through utilization, power availability, maintenance and payment operations, not through charger installation alone.
  • The source identifies an opportunity area rather than a validated customer problem. A useful first step is to choose one actor, workflow and measurable failure.

Possible starting points

01

Fleet-depot charging

Optimize power, schedules and charger uptime for a concentrated commercial fleet with predictable routes.

02

Charging operations layer

Monitor faults, service technicians, payments and energy use across equipment from multiple vendors.

Questions to answer

  1. Which vehicle segment can produce dependable utilization at the first sites?
  2. Who pays for upgrades, downtime and maintenance across the property, fleet and charging operator?
No. 1113Problem statementMobility and logistics

Development of a versatile and fast algorithm for the optimal ship routing

Develop a reasonably fast, adaptable ship-route optimisation algorithm for voyages between Indian Ocean ports. Start with journey time and weather safety while allowing further objectives such as fuel and comfort. Account for changing wind, waves and currents and differences in vessel design/dimensions/drift, updating the route as conditions evolve. An open-source language such as Python is preferred; no particular optimisation method is mandated.

No. 1239Problem statementMobility and logistics

Development of an Intelligent Freight Forecasting Model for Optimized Vessel Chartering and Bulk Cargo Procurement from overseas to East Coast of India

The freight model should help bulk-cargo procurers serving India's East Coast move from repeated spot bookings to short- or medium-term multiple-voyage charters. It should forecast rates and market-entry windows, recommend vessel classes and manage idle-positioning risk using trade, economic, seasonal and congestion data. Loading and discharge port constraints, including draft, vessel length, beam and cargo-handling capacity, must inform recommendations. Machine learning and AI are possible methods, not mandatory exclusive approaches.

No. 1352Problem statementMobility and logistics

Edge-AI Based Distributed Fleet Coordination for Autonomous Mobile Robots (AMRs) in Smart Warehouses

Develop decentralised warehouse-fleet coordination for at least three AMRs, running locally on onboard edge hardware. Robots exchange position/intent directly, resolve intersection deadlocks, avoid collisions and reassign tasks or routes around blocked aisles without a central server. Deliver a multi-robot simulation with peer networking, edge-compatible planning and a dashboard showing positions and batteries. The source targets zero inter-robot collisions and at least 20% faster task completion than stop-and-wait on overlapping routes; these are test criteria.