Pune, June 5: Intangles, a global AI-powered predictive intelligence company specialising in the commercial vehicle domain, released an analysis of commercial vehicle performance on the Mumbai-Pune corridor following the opening of the Connecting Link. The analysis indicates that improved corridor movement could generate 2.7 crore litres in potential annual fuel savings, translating into approximately ₹272 crore in annual fuel cost reduction across corridor stretch.
The estimated fuel savings could also help avoid 64,905 metric tonnes of CO₂ emissions annually. Together, the findings point to the wider economic and environmental value of smoother movement on a corridor critical to the Mumbai-Pune-Bangalore route and Maharashtra’s freight and passenger economy.
The analysis recorded performance gains across the four commercial vehicle categories studied: buses, MCV trucks, three-axle vehicles and multi-axle trucks. MCV trucks recorded the highest increase in average speed at 18%, alongside a 19% reduction in travel time and 17% reduction in fuel consumption. Three-axle vehicles saw the highest reduction in travel time at 20%, while buses achieved the strongest improvement in fuel consumption at 24% per trip. Multi-axle trucks also recorded gains across speed, travel time and fuel use, indicating that improved corridor movement can create value across heavier vehicle categories too.
Anup Patil, CEO, Intangles, said,
“Fuel is a direct measure of operational efficiency, and on a corridor carrying this volume of freight, even modest per-trip savings compound into material economic impact. What this analysis demonstrates is that vehicle data, collected and processed at scale, can quantify infrastructure value in the terms that actually matter to fleet operators: litres saved, minutes recovered, emissions reduced. At Intangles, we build predictive intelligence using our proprietary digital twin technology that helps fleets capture this value continuously, not just when a new road opens, but across every route, every trip, and every vehicle in operation. India’s infrastructure investment is accelerating. It is just a matter of time that the fleets that deploy advanced intelligence will benefit vastly alongside India’s growth story.”
Hariharan Ravishankar, Chief AI Scientist, Intangles, added,
“Most infrastructure impact assessments rely on modelled assumptions with fixed consumption rates applied to traffic volumes. What makes this analysis different is that every fuel figure comes from actual vehicle sensor streams, processed through terrain-aware algorithms that account for gradient, load behaviour, and real-time driving patterns. The finding that heavier vehicle categories showed the strongest proportional gains is not intuitive, but it is exactly what the physics predicts. Vehicles most constrained by stop-go conditions on steep gradients benefit most when that constraint is removed. As India’s transport infrastructure expands, this kind of sensor-based measurement framework gives planners, operators, and policymakers something they have not had before: infrastructure ROI expressed in operating terms, not projections.”
The analysis also observed an early reduction in hard braking events across the commercial vehicle categories studied. While these findings require longer-term tracking before conclusions can be drawn on sustained safety impact, they provide an early indication of improved driving conditions on the stretch in consideration.
Methodology
The analysis tracked 1,849 unique commercial vehicles across buses, MCV trucks, 3-axle vehicles and multi-axle trucks, covering more than 2,200 trips through the ghat section of the Mumbai-Pune corridor. Vehicle performance was compared across two periods: 26 to 30 April 2026, before the Connecting Link opening, and 2 to 15 May 2026, after the opening, allowing one day for traffic stabilisation. Speed and travel time were measured through GPS and geo-location data. Fuel consumption for the assessed commercial vehicle categories was derived using Intangles’ proprietary algorithms based on terrain analysis and real-time driving patterns.